Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4029 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4505. Min Range: -8.4505
Max Act: 8.4505. Min Act: -0.1700
Data Index: 2016504 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4505. Min Range: -8.4505
Max Act: 8.1380. Min Act: -0.1700
Data Index: 5127113 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4505. Min Range: -8.4505
Max Act: 8.1380. Min Act: -0.1700
Data Index: 147580 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.9505. Min Act: -0.1700
Data Index: 1788093 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.8880. Min Act: -0.1700
Data Index: 3623894 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.8880. Min Act: -0.1700
Data Index: 1908315 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.8255. Min Act: -0.1700
Data Index: 8002354 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.8255. Min Act: -0.1700
Data Index: 7140582 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.7630. Min Act: -0.1700
Data Index: 1807161 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6692. Min Act: -0.1700
Data Index: 5447734 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6692. Min Act: -0.1700
Data Index: 1204815 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6692. Min Act: -0.1700
Data Index: 3248364 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6380. Min Act: -0.1700
Data Index: 7095121 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6380. Min Act: -0.1700
Data Index: 4436734 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6380. Min Act: -0.1700
Data Index: 1728224 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.6380. Min Act: -0.1700
Data Index: 1258607 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.5755. Min Act: -0.1700
Data Index: 5167221 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.5755. Min Act: -0.1700
Data Index: 819201 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.5755. Min Act: -0.1700
Data Index: 626705 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4505. Min Range: -8.4505
Max Act: 7.5442. Min Act: -0.1700
Data Index: 3632180 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19