Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1637 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0871. Min Range: -7.0871
Max Act: 7.0871. Min Act: -0.1700
Data Index: 1114434 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.8371. Min Act: -0.1700
Data Index: 2296012 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.7434. Min Act: -0.1700
Data Index: 7626475 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6809. Min Act: -0.1700
Data Index: 995911 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6496. Min Act: -0.1700
Data Index: 8829790 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6496. Min Act: -0.1700
Data Index: 5045801 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6496. Min Act: -0.1700
Data Index: 3015165 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6184. Min Act: -0.1700
Data Index: 6228692 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6184. Min Act: -0.1700
Data Index: 6451032 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6184. Min Act: -0.1700
Data Index: 498459 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.6496. Min Act: -0.1700
Data Index: 2844911 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5871. Min Act: -0.1700
Data Index: 6448377 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5871. Min Act: -0.1700
Data Index: 1044368 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5871. Min Act: -0.1700
Data Index: 1457227 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5871. Min Act: -0.1700
Data Index: 1725592 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5559. Min Act: -0.1700
Data Index: 2280713 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5559. Min Act: -0.1700
Data Index: 4770534 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5559. Min Act: -0.1700
Data Index: 2104849 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.5246. Min Act: -0.1700
Data Index: 1858774 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0871. Min Range: -7.0871
Max Act: 6.4934. Min Act: -0.1700
Data Index: 171091 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19