Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0126. Min Range: -7.0126
Max Act: 7.0126. Min Act: -0.1700
Data Index: 8754779 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6676907 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6608906 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.8876. Min Act: -0.1700
Data Index: 6652102 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.7938. Min Act: -0.1700
Data Index: 3548538 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.7938. Min Act: -0.1700
Data Index: 4558863 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.7626. Min Act: -0.1700
Data Index: 5220425 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.7626. Min Act: -0.1700
Data Index: 5733259 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.7001. Min Act: -0.1700
Data Index: 8243416 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6688. Min Act: -0.1700
Data Index: 3028820 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6688. Min Act: -0.1700
Data Index: 7968992 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6688. Min Act: -0.1700
Data Index: 1813403 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6688. Min Act: -0.1700
Data Index: 2184375 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6376. Min Act: -0.1700
Data Index: 7101922 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6376. Min Act: -0.1700
Data Index: 4026971 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.6063. Min Act: -0.1700
Data Index: 7115118 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.5751. Min Act: -0.1700
Data Index: 4935154 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.5751. Min Act: -0.1700
Data Index: 1286981 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.5438. Min Act: -0.1700
Data Index: 2239341 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0126. Min Range: -7.0126
Max Act: 6.5751. Min Act: -0.1700
Data Index: 8252485 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19