Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.9598. Min Act: -0.1700
Data Index: 2827896 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.8973. Min Act: -0.1700
Data Index: 7251420 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.8348. Min Act: -0.1700
Data Index: 5152280 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.8348. Min Act: -0.1700
Data Index: 5879042 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.7723. Min Act: -0.1700
Data Index: 5413965 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.7723. Min Act: -0.1700
Data Index: 1077204 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.7098. Min Act: -0.1700
Data Index: 3727610 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.6473. Min Act: -0.1700
Data Index: 3381386 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.6473. Min Act: -0.1700
Data Index: 4012983 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.5848. Min Act: -0.1700
Data Index: 7265926 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.5848. Min Act: -0.1700
Data Index: 6725184 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.5848. Min Act: -0.1700
Data Index: 7157454 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.4598. Min Act: -0.1700
Data Index: 5861757 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.5223. Min Act: -0.1700
Data Index: 6175735 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.3973. Min Act: -0.1700
Data Index: 1481472 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.4598. Min Act: -0.1700
Data Index: 3712728 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.4598. Min Act: -0.1700
Data Index: 4078878 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.3973. Min Act: -0.1700
Data Index: 73331 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.3973. Min Act: -0.1700
Data Index: 1606594 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9598. Min Range: -8.9598
Max Act: 8.3348. Min Act: -0.1700
Data Index: 2558561 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19