Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2178. Min Range: -6.2178
Max Act: 6.2178. Min Act: -0.1700
Data Index: 2391522 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2178. Min Range: -6.2178
Max Act: 6.1241. Min Act: -0.1700
Data Index: 330679 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2178. Min Range: -6.2178
Max Act: 6.0303. Min Act: -0.1700
Data Index: 5320433 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.9991. Min Act: -0.1700
Data Index: 4142837 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.9678. Min Act: -0.1700
Data Index: 852202 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.9053. Min Act: -0.1700
Data Index: 6327846 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.9366. Min Act: -0.1700
Data Index: 8193645 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4119439 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8741. Min Act: -0.1700
Data Index: 5964110 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8741. Min Act: -0.1700
Data Index: 5475542 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8741. Min Act: -0.1700
Data Index: 3611265 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8428. Min Act: -0.1700
Data Index: 2457850 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8428. Min Act: -0.1700
Data Index: 5964055 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8116. Min Act: -0.1700
Data Index: 1868683 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.7803. Min Act: -0.1700
Data Index: 3192184 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8428. Min Act: -0.1700
Data Index: 3586363 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.8116. Min Act: -0.1700
Data Index: 7530858 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.7803. Min Act: -0.1700
Data Index: 2179694 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4292679 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2178. Min Range: -6.2178
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4594807 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19