Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.6336. Min Act: -0.1700
Data Index: 2595218 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.5711. Min Act: -0.1700
Data Index: 7707125 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.3836. Min Act: -0.1700
Data Index: 6669628 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.3836. Min Act: -0.1700
Data Index: 3040445 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.3524. Min Act: -0.1700
Data Index: 616150 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.3211. Min Act: -0.1700
Data Index: 2143723 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 984259 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 4656847 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 5601854 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 7651022 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 8629003 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2586. Min Act: -0.1700
Data Index: 3787763 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2274. Min Act: -0.1700
Data Index: 6989505 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.2274. Min Act: -0.1700
Data Index: 5889237 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1961. Min Act: -0.1700
Data Index: 4049818 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1961. Min Act: -0.1700
Data Index: 6346079 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1961. Min Act: -0.1700
Data Index: 8268568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1961. Min Act: -0.1700
Data Index: 7655290 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1649. Min Act: -0.1700
Data Index: 6191351 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6336. Min Range: -6.6336
Max Act: 6.1649. Min Act: -0.1700
Data Index: 1208169 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19