Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9427. Min Range: -7.9427
Max Act: 7.9427. Min Act: -0.1700
Data Index: 731145 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9427. Min Range: -7.9427
Max Act: 7.0677. Min Act: -0.1700
Data Index: 6840917 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.8802. Min Act: -0.1700
Data Index: 4085293 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.7864. Min Act: -0.1700
Data Index: 8604830 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.7864. Min Act: -0.1700
Data Index: 6893982 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.6927. Min Act: -0.1700
Data Index: 8703051 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.6614. Min Act: -0.1700
Data Index: 122762 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.6614. Min Act: -0.1700
Data Index: 8431705 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.6614. Min Act: -0.1700
Data Index: 5734987 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.6302. Min Act: -0.1700
Data Index: 8638122 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.5364. Min Act: -0.1700
Data Index: 3259796 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.5364. Min Act: -0.1700
Data Index: 7735071 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1683875 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1543217 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.4739. Min Act: -0.1700
Data Index: 5182210 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.4739. Min Act: -0.1700
Data Index: 1966573 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.5052. Min Act: -0.1700
Data Index: 3066187 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.4739. Min Act: -0.1700
Data Index: 7419954 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.4739. Min Act: -0.1700
Data Index: 510675 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9427. Min Range: -7.9427
Max Act: 6.4427. Min Act: -0.1700
Data Index: 7459493 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19