Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 954 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.6272. Min Act: -0.1700
Data Index: 7921284 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5960. Min Act: -0.1700
Data Index: 7864063 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5647. Min Act: -0.1700
Data Index: 5360007 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5647. Min Act: -0.1700
Data Index: 5373155 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5647. Min Act: -0.1700
Data Index: 3400743 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5335. Min Act: -0.1700
Data Index: 7665987 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5335. Min Act: -0.1700
Data Index: 6516226 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5647. Min Act: -0.1700
Data Index: 1861738 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5647. Min Act: -0.1700
Data Index: 8313495 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5335. Min Act: -0.1700
Data Index: 6119746 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5335. Min Act: -0.1700
Data Index: 733232 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 6710066 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 385467 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 3010165 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 6119747 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 4852514 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.5022. Min Act: -0.1700
Data Index: 1981145 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 1721434 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 4017861 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6272. Min Range: -4.6272
Max Act: 4.4710. Min Act: -0.1700
Data Index: 8317507 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19