Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.5687. Min Act: -0.1700
Data Index: 938988 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.2562. Min Act: -0.1700
Data Index: 7995190 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1937. Min Act: -0.1700
Data Index: 6290673 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.2562. Min Act: -0.1700
Data Index: 1700881 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 3363208 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1937. Min Act: -0.1700
Data Index: 5713188 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 4637739 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.2249. Min Act: -0.1700
Data Index: 2618887 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1937. Min Act: -0.1700
Data Index: 4183795 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.2249. Min Act: -0.1700
Data Index: 1710196 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 8813510 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1937. Min Act: -0.1700
Data Index: 7172668 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 3085857 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 8671715 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1312. Min Act: -0.1700
Data Index: 5657863 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1312. Min Act: -0.1700
Data Index: 3828671 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1312. Min Act: -0.1700
Data Index: 8359037 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1624. Min Act: -0.1700
Data Index: 8275341 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1312. Min Act: -0.1700
Data Index: 918307 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5687. Min Range: -7.5687
Max Act: 7.1312. Min Act: -0.1700
Data Index: 6693017 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19