Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6257 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.5614. Min Act: -0.1700
Data Index: 1517011 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.5614. Min Act: -0.1700
Data Index: 99816 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.5301. Min Act: -0.1700
Data Index: 7622445 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.4676. Min Act: -0.1700
Data Index: 8712802 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.4364. Min Act: -0.1700
Data Index: 5636999 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.3739. Min Act: -0.1700
Data Index: 2218254 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.3426. Min Act: -0.1700
Data Index: 3802377 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.2801. Min Act: -0.1700
Data Index: 202813 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.2489. Min Act: -0.1700
Data Index: 2473448 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.2176. Min Act: -0.1700
Data Index: 1950866 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.1864. Min Act: -0.1700
Data Index: 5343042 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.1864. Min Act: -0.1700
Data Index: 5243733 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.1551. Min Act: -0.1700
Data Index: 1975770 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0926. Min Act: -0.1700
Data Index: 737739 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0926. Min Act: -0.1700
Data Index: 5993065 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0926. Min Act: -0.1700
Data Index: 4316445 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0614. Min Act: -0.1700
Data Index: 192438 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0301. Min Act: -0.1700
Data Index: 1700822 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0301. Min Act: -0.1700
Data Index: 7679919 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5614. Min Range: -7.5614
Max Act: 7.0301. Min Act: -0.1700
Data Index: 4357944 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19