Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.3521. Min Act: -0.1700
Data Index: 3685705 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.2896. Min Act: -0.1700
Data Index: 5929112 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.2271. Min Act: -0.1700
Data Index: 4698860 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.1958. Min Act: -0.1700
Data Index: 8748476 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.1646. Min Act: -0.1700
Data Index: 3667581 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.1646. Min Act: -0.1700
Data Index: 7986794 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.1021. Min Act: -0.1700
Data Index: 7444529 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.1333. Min Act: -0.1700
Data Index: 7746196 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0396. Min Act: -0.1700
Data Index: 1862078 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0396. Min Act: -0.1700
Data Index: 8508527 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9771. Min Act: -0.1700
Data Index: 322083 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0083. Min Act: -0.1700
Data Index: 6811602 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0083. Min Act: -0.1700
Data Index: 96718 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0083. Min Act: -0.1700
Data Index: 983346 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9771. Min Act: -0.1700
Data Index: 426583 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9771. Min Act: -0.1700
Data Index: 216098 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9771. Min Act: -0.1700
Data Index: 2673245 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9771. Min Act: -0.1700
Data Index: 5716423 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3521. Min Range: -5.3521
Max Act: 5.0083. Min Act: -0.1700
Data Index: 3453424 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3521. Min Range: -5.3521
Max Act: 4.9458. Min Act: -0.1700
Data Index: 3760743 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19