Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 358 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.9658. Min Act: -0.1700
Data Index: 1181725 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.8720. Min Act: -0.1700
Data Index: 1132799 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.8408. Min Act: -0.1700
Data Index: 5727013 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.7158. Min Act: -0.1700
Data Index: 6636886 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.6220. Min Act: -0.1700
Data Index: 5840855 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.5595. Min Act: -0.1700
Data Index: 6853796 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.5283. Min Act: -0.1700
Data Index: 8810674 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.4345. Min Act: -0.1700
Data Index: 6988482 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.3408. Min Act: -0.1700
Data Index: 3176476 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.2783. Min Act: -0.1700
Data Index: 4090555 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.2470. Min Act: -0.1700
Data Index: 506282 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.1533. Min Act: -0.1700
Data Index: 1370474 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.1845. Min Act: -0.1700
Data Index: 1188044 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.1533. Min Act: -0.1700
Data Index: 2518469 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.1220. Min Act: -0.1700
Data Index: 3219139 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.0908. Min Act: -0.1700
Data Index: 2229307 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.9970. Min Act: -0.1700
Data Index: 3922824 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.0283. Min Act: -0.1700
Data Index: 4219025 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.9970. Min Act: -0.1700
Data Index: 3758315 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.9658. Min Act: -0.1700
Data Index: 8225903 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19