Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0033. Min Range: -6.0033
Max Act: 6.0033. Min Act: -0.1700
Data Index: 8702131 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.9721. Min Act: -0.1700
Data Index: 2377821 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.7846. Min Act: -0.1700
Data Index: 5845694 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6908. Min Act: -0.1700
Data Index: 7504136 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3250257 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3939805 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3875574 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5971. Min Act: -0.1700
Data Index: 6966118 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5971. Min Act: -0.1700
Data Index: 636388 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5971. Min Act: -0.1700
Data Index: 2695408 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5033. Min Act: -0.1700
Data Index: 44234 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5346. Min Act: -0.1700
Data Index: 410474 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.5033. Min Act: -0.1700
Data Index: 7363190 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4721. Min Act: -0.1700
Data Index: 8530191 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4721. Min Act: -0.1700
Data Index: 4921406 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4721. Min Act: -0.1700
Data Index: 649032 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4408. Min Act: -0.1700
Data Index: 7495278 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4096. Min Act: -0.1700
Data Index: 817004 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4096. Min Act: -0.1700
Data Index: 3995258 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0033. Min Range: -6.0033
Max Act: 5.4096. Min Act: -0.1700
Data Index: 5211105 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19