Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.9407. Min Act: -0.1700
Data Index: 1370940 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.8782. Min Act: -0.1700
Data Index: 8735995 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.8469. Min Act: -0.1700
Data Index: 75373 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.8469. Min Act: -0.1700
Data Index: 6781500 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.8157. Min Act: -0.1700
Data Index: 8656276 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.8157. Min Act: -0.1700
Data Index: 3000762 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.7844. Min Act: -0.1700
Data Index: 6305792 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.7844. Min Act: -0.1699
Data Index: 7770873 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.7219. Min Act: -0.1700
Data Index: 4815734 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.7532. Min Act: -0.1700
Data Index: 5271677 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.7219. Min Act: -0.1700
Data Index: 6319096 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6907. Min Act: -0.1700
Data Index: 8327730 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6907. Min Act: -0.1700
Data Index: 8832065 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6907. Min Act: -0.1700
Data Index: 4490876 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 379587 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1675641 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 3713327 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1313745 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 2762083 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9407. Min Range: -5.9407
Max Act: 5.6594. Min Act: -0.1700
Data Index: 864606 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19