Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4164 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.6313. Min Act: -0.1700
Data Index: 3535635 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3963. Min Act: -0.1700
Data Index: 467932 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3806. Min Act: -0.1700
Data Index: 8241827 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3179. Min Act: -0.1700
Data Index: 882450 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3179. Min Act: -0.1700
Data Index: 1757564 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3179. Min Act: -0.1700
Data Index: 3894882 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3179. Min Act: -0.1700
Data Index: 4893397 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.3022. Min Act: -0.1700
Data Index: 2970881 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2551. Min Act: -0.1700
Data Index: 3708621 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2551. Min Act: -0.1700
Data Index: 7951893 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2551. Min Act: -0.1700
Data Index: 1260596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2237. Min Act: -0.1700
Data Index: 7961444 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2237. Min Act: -0.1700
Data Index: 7139991 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2237. Min Act: -0.1700
Data Index: 6929788 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.2079. Min Act: -0.1700
Data Index: 1972756 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.1765. Min Act: -0.1700
Data Index: 8303407 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.1765. Min Act: -0.1700
Data Index: 1670793 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.1922. Min Act: -0.1700
Data Index: 6611491 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.1922. Min Act: -0.1700
Data Index: 8393529 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6313. Min Range: -3.6313
Max Act: 3.1765. Min Act: -0.1700
Data Index: 3894875 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19