Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.2371. Min Act: -0.1700
Data Index: 1377041 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1433. Min Act: -0.1700
Data Index: 3297107 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1121. Min Act: -0.1700
Data Index: 4997306 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0808. Min Act: -0.1700
Data Index: 1285490 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0808. Min Act: -0.1700
Data Index: 4329019 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0496. Min Act: -0.1700
Data Index: 1901422 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0496. Min Act: -0.1700
Data Index: 2484172 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0808. Min Act: -0.1700
Data Index: 7635633 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0496. Min Act: -0.1700
Data Index: 1109982 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0183. Min Act: -0.1700
Data Index: 7278697 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0496. Min Act: -0.1700
Data Index: 6378132 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0183. Min Act: -0.1700
Data Index: 6852589 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0183. Min Act: -0.1700
Data Index: 2090358 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0183. Min Act: -0.1700
Data Index: 20704 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0183. Min Act: -0.1700
Data Index: 5614991 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9871. Min Act: -0.1700
Data Index: 7489434 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9871. Min Act: -0.1700
Data Index: 3672333 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9871. Min Act: -0.1700
Data Index: 1976258 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9871. Min Act: -0.1700
Data Index: 240473 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9871. Min Act: -0.1700
Data Index: 7576567 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19