Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1264. Min Range: -8.1264
Max Act: 8.1264. Min Act: -0.1700
Data Index: 3974402 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8764. Min Act: -0.1700
Data Index: 8199710 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8764. Min Act: -0.1700
Data Index: 7887537 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8139. Min Act: -0.1700
Data Index: 3238102 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8139. Min Act: -0.1700
Data Index: 150507 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8139. Min Act: -0.1700
Data Index: 2689807 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.8139. Min Act: -0.1700
Data Index: 141248 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 8238888 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 2917505 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 3301701 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 6469791 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.7514. Min Act: -0.1700
Data Index: 6106534 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6889. Min Act: -0.1700
Data Index: 7461418 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 8532831 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 5125566 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 269466 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 3063866 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6889. Min Act: -0.1700
Data Index: 3050695 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 8172177 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1264. Min Range: -8.1264
Max Act: 7.6264. Min Act: -0.1700
Data Index: 1392038 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19