Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.7125. Min Act: -0.1700
Data Index: 6783344 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.5875. Min Act: -0.1700
Data Index: 8510021 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4938. Min Act: -0.1700
Data Index: 2239445 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4938. Min Act: -0.1700
Data Index: 368160 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2842305 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8052737 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4000. Min Act: -0.1700
Data Index: 627733 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4000. Min Act: -0.1700
Data Index: 3448225 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.4000. Min Act: -0.1700
Data Index: 694204 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3688. Min Act: -0.1700
Data Index: 2641705 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3063. Min Act: -0.1700
Data Index: 7344582 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3375. Min Act: -0.1700
Data Index: 8376658 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3063. Min Act: -0.1700
Data Index: 1719749 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3375. Min Act: -0.1700
Data Index: 825424 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.3063. Min Act: -0.1700
Data Index: 5327216 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.2750. Min Act: -0.1700
Data Index: 4384048 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.2750. Min Act: -0.1700
Data Index: 1841070 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.2438. Min Act: -0.1700
Data Index: 1818443 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.2125. Min Act: -0.1700
Data Index: 8477405 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7125. Min Range: -6.7125
Max Act: 6.2438. Min Act: -0.1700
Data Index: 8265655 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19