Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6381 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2819951 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.6132. Min Act: -0.1700
Data Index: 567942 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5507. Min Act: -0.1700
Data Index: 6350687 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.5194. Min Act: -0.1700
Data Index: 6318654 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 2527101 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4882. Min Act: -0.1700
Data Index: 194718 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4882. Min Act: -0.1700
Data Index: 48971 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4882. Min Act: -0.1700
Data Index: 5326363 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 2527105 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 7823441 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 6470566 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 1887358 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 6318653 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 3216796 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1887360 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 2696113 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 585783 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4569. Min Act: -0.1700
Data Index: 8710029 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 48975 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6444. Min Range: -4.6444
Max Act: 4.4257. Min Act: -0.1700
Data Index: 2527102 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19