Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2364. Min Range: -7.2364
Max Act: 7.2364. Min Act: -0.1700
Data Index: 1980460 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2364. Min Range: -7.2364
Max Act: 7.1426. Min Act: -0.1700
Data Index: 7919130 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2364. Min Range: -7.2364
Max Act: 7.0801. Min Act: -0.1700
Data Index: 8196603 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.9864. Min Act: -0.1700
Data Index: 1144624 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.9864. Min Act: -0.1700
Data Index: 7173890 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.9864. Min Act: -0.1700
Data Index: 7770491 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.9239. Min Act: -0.1700
Data Index: 4652986 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.9551. Min Act: -0.1698
Data Index: 1558939 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 2154467 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 7499921 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 2128213 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 2814411 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 3523212 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8614. Min Act: -0.1700
Data Index: 8483364 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8926. Min Act: -0.1700
Data Index: 8731136 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8614. Min Act: -0.1700
Data Index: 8289830 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8301. Min Act: -0.1700
Data Index: 8678780 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8301. Min Act: -0.1700
Data Index: 1632353 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8301. Min Act: -0.1700
Data Index: 6350695 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2364. Min Range: -7.2364
Max Act: 6.8301. Min Act: -0.1700
Data Index: 156838 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19