Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.1651. Min Range: -11.1651
Max Act: 11.1651. Min Act: -0.1700
Data Index: 1815230 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.9776. Min Act: -0.1700
Data Index: 75962 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.9776. Min Act: -0.1700
Data Index: 2148211 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.9151. Min Act: -0.1700
Data Index: 6355670 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.8526. Min Act: -0.1700
Data Index: 2025255 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.7276. Min Act: -0.1700
Data Index: 2025699 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.7901. Min Act: -0.1700
Data Index: 4128142 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6651. Min Act: -0.1700
Data Index: 6910045 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.7901. Min Act: -0.1700
Data Index: 7205518 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6026. Min Act: -0.1700
Data Index: 5865996 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6651. Min Act: -0.1700
Data Index: 8359768 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6026. Min Act: -0.1700
Data Index: 8813266 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6651. Min Act: -0.1700
Data Index: 1721699 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.7276. Min Act: -0.1700
Data Index: 17859 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6026. Min Act: -0.1700
Data Index: 7448646 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6026. Min Act: -0.1700
Data Index: 5889434 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.5401. Min Act: -0.1700
Data Index: 6580372 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.5401. Min Act: -0.1700
Data Index: 8620151 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.6026. Min Act: -0.1700
Data Index: 2949090 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1651. Min Range: -11.1651
Max Act: 10.4151. Min Act: -0.1700
Data Index: 7321216 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19