Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6643. Min Range: -7.6643
Max Act: 7.6643. Min Act: -0.1700
Data Index: 8260643 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6643. Min Range: -7.6643
Max Act: 7.1643. Min Act: -0.1700
Data Index: 7673893 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6643. Min Range: -7.6643
Max Act: 7.0393. Min Act: -0.1700
Data Index: 2893009 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.9143. Min Act: -0.1700
Data Index: 4980633 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.9143. Min Act: -0.1700
Data Index: 6087772 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.9143. Min Act: -0.1700
Data Index: 8637920 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.8206. Min Act: -0.1700
Data Index: 4416687 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.8206. Min Act: -0.1700
Data Index: 4843604 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7581. Min Act: -0.1700
Data Index: 4644644 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7581. Min Act: -0.1700
Data Index: 6192387 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7581. Min Act: -0.1700
Data Index: 6893212 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1006954 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1792630 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7581. Min Act: -0.1700
Data Index: 1231598 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 7966489 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 8188305 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 2992439 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.7268. Min Act: -0.1700
Data Index: 7486896 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.6956. Min Act: -0.1700
Data Index: 4695396 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6643. Min Range: -7.6643
Max Act: 6.6956. Min Act: -0.1700
Data Index: 1866072 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19