Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6336 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.2583. Min Act: -0.1700
Data Index: 926307 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9771. Min Act: -0.1700
Data Index: 1421374 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8521. Min Act: -0.1700
Data Index: 1427107 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8208. Min Act: -0.1700
Data Index: 6525248 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.7896. Min Act: -0.1700
Data Index: 5524228 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.6958. Min Act: -0.1700
Data Index: 5182865 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.6958. Min Act: -0.1700
Data Index: 4900398 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.6646. Min Act: -0.1700
Data Index: 3437317 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.5708. Min Act: -0.1700
Data Index: 7957121 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.5708. Min Act: -0.1700
Data Index: 7122046 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.5083. Min Act: -0.1700
Data Index: 82473 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.4771. Min Act: -0.1700
Data Index: 5715004 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.4458. Min Act: -0.1700
Data Index: 1298413 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.4146. Min Act: -0.1700
Data Index: 3404412 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.3833. Min Act: -0.1700
Data Index: 4772921 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.4146. Min Act: -0.1700
Data Index: 7011053 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.3833. Min Act: -0.1700
Data Index: 8283361 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.3521. Min Act: -0.1700
Data Index: 7380009 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.3833. Min Act: -0.1700
Data Index: 6172651 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.3521. Min Act: -0.1700
Data Index: 6698051 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19