Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5388 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.4585. Min Act: -0.1700
Data Index: 7536806 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.3960. Min Act: -0.1700
Data Index: 4225389 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.3960. Min Act: -0.1700
Data Index: 2100179 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.2085. Min Act: -0.1700
Data Index: 8494054 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.1460. Min Act: -0.1700
Data Index: 6201583 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.1460. Min Act: -0.1700
Data Index: 6014040 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.1460. Min Act: -0.1700
Data Index: 577624 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0835. Min Act: -0.1700
Data Index: 8534953 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0210. Min Act: -0.1700
Data Index: 6566697 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0835. Min Act: -0.1700
Data Index: 5510339 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0210. Min Act: -0.1700
Data Index: 968081 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.9585. Min Act: -0.1700
Data Index: 3894726 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0210. Min Act: -0.1700
Data Index: 1690048 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4585. Min Range: -9.4585
Max Act: 9.0210. Min Act: -0.1700
Data Index: 8730241 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.9585. Min Act: -0.1700
Data Index: 3571803 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.8960. Min Act: -0.1700
Data Index: 7651954 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.8960. Min Act: -0.1700
Data Index: 3647341 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.8960. Min Act: -0.1700
Data Index: 7894765 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.8960. Min Act: -0.1700
Data Index: 4950158 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4585. Min Range: -9.4585
Max Act: 8.8960. Min Act: -0.1700
Data Index: 5368029 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19