Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0526. Min Range: -6.0526
Max Act: 6.0526. Min Act: -0.1700
Data Index: 2807816 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.9589. Min Act: -0.1700
Data Index: 1684534 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.8651. Min Act: -0.1700
Data Index: 7871290 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.7089. Min Act: -0.1700
Data Index: 3476481 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6464. Min Act: -0.1700
Data Index: 1383835 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.6464. Min Act: -0.1700
Data Index: 5570289 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5839. Min Act: -0.1700
Data Index: 7752716 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5839. Min Act: -0.1700
Data Index: 1649319 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5214. Min Act: -0.1700
Data Index: 6073554 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.5214. Min Act: -0.1700
Data Index: 8182844 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4901. Min Act: -0.1700
Data Index: 2699506 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4901. Min Act: -0.1700
Data Index: 7908830 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4589. Min Act: -0.1700
Data Index: 632734 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4589. Min Act: -0.1700
Data Index: 1281370 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4589. Min Act: -0.1700
Data Index: 5121901 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4589. Min Act: -0.1700
Data Index: 3544010 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4589. Min Act: -0.1700
Data Index: 7372708 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4276. Min Act: -0.1700
Data Index: 5743278 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4276. Min Act: -0.1700
Data Index: 7839296 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0526. Min Range: -6.0526
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3899972 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19