Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4116 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2785058 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3656822 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8773219 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7071. Min Act: -0.1700
Data Index: 5972138 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7071. Min Act: -0.1700
Data Index: 4496224 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6759. Min Act: -0.1700
Data Index: 2663920 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5821. Min Act: -0.1700
Data Index: 7211799 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5509. Min Act: -0.1700
Data Index: 7565951 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5196. Min Act: -0.1700
Data Index: 7584035 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4884. Min Act: -0.1700
Data Index: 8666283 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4571. Min Act: -0.1700
Data Index: 2565186 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4884. Min Act: -0.1700
Data Index: 2908021 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5196. Min Act: -0.1700
Data Index: 5954173 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4571. Min Act: -0.1700
Data Index: 2476410 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4571. Min Act: -0.1700
Data Index: 3613370 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4259. Min Act: -0.1700
Data Index: 8637404 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1886942 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.3946. Min Act: -0.1700
Data Index: 4505670 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4571. Min Act: -0.1700
Data Index: 4520544 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4259. Min Act: -0.1700
Data Index: 8750926 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19