Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.2504. Min Act: -0.1700
Data Index: 8225413 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7711386 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.2191. Min Act: -0.1700
Data Index: 7438470 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1566. Min Act: -0.1700
Data Index: 1693451 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1879. Min Act: -0.1700
Data Index: 8519147 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1566. Min Act: -0.1700
Data Index: 5957376 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1566. Min Act: -0.1700
Data Index: 7123018 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1566. Min Act: -0.1700
Data Index: 6740575 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1254. Min Act: -0.1700
Data Index: 7636722 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1566. Min Act: -0.1700
Data Index: 7438468 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1879. Min Act: -0.1700
Data Index: 7438469 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.1254. Min Act: -0.1700
Data Index: 3213971 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0941. Min Act: -0.1700
Data Index: 7438467 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0629. Min Act: -0.1700
Data Index: 3015550 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0629. Min Act: -0.1700
Data Index: 7666104 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0941. Min Act: -0.1700
Data Index: 4196543 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0316. Min Act: -0.1700
Data Index: 6656043 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0316. Min Act: -0.1700
Data Index: 1230906 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0004. Min Act: -0.1700
Data Index: 6464062 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2504. Min Range: -5.2504
Max Act: 5.0004. Min Act: -0.1700
Data Index: 4367779 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19