Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.6461. Min Act: -0.1700
Data Index: 8046608 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.5211. Min Act: -0.1700
Data Index: 4492275 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.5211. Min Act: -0.1700
Data Index: 2537991 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.5836. Min Act: -0.1700
Data Index: 1036850 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.4274. Min Act: -0.1700
Data Index: 1241557 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3961. Min Act: -0.1700
Data Index: 7774280 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3961. Min Act: -0.1700
Data Index: 4056048 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3649. Min Act: -0.1700
Data Index: 8235399 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3649. Min Act: -0.1700
Data Index: 5810827 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3024. Min Act: -0.1700
Data Index: 3959215 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3336. Min Act: -0.1700
Data Index: 4631094 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3336. Min Act: -0.1700
Data Index: 5567776 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3649. Min Act: -0.1700
Data Index: 5186995 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3024. Min Act: -0.1700
Data Index: 7512304 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.2711. Min Act: -0.1700
Data Index: 114324 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.3024. Min Act: -0.1700
Data Index: 552423 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.2711. Min Act: -0.1700
Data Index: 1772694 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.2711. Min Act: -0.1700
Data Index: 7073065 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.2711. Min Act: -0.1700
Data Index: 1438193 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6461. Min Range: -8.6461
Max Act: 8.2399. Min Act: -0.1700
Data Index: 105623 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19