Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.9091. Min Act: -0.1700
Data Index: 4673814 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.7371. Min Act: -0.1700
Data Index: 5316065 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.7371. Min Act: -0.1700
Data Index: 6042819 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.7214. Min Act: -0.1700
Data Index: 995798 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.6745. Min Act: -0.1700
Data Index: 6700183 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.5493. Min Act: -0.1700
Data Index: 7564464 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.5336. Min Act: -0.1700
Data Index: 6247621 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4866. Min Act: -0.1700
Data Index: 439548 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.5023. Min Act: -0.1700
Data Index: 6577421 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.5023. Min Act: -0.1700
Data Index: 6878132 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4866. Min Act: -0.1700
Data Index: 7901463 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4710. Min Act: -0.1700
Data Index: 3913443 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4710. Min Act: -0.1700
Data Index: 7765440 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4553. Min Act: -0.1700
Data Index: 4279166 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4710. Min Act: -0.1700
Data Index: 6911333 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4710. Min Act: -0.1700
Data Index: 8469863 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4553. Min Act: -0.1700
Data Index: 7624930 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4240. Min Act: -0.1700
Data Index: 6034161 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4396. Min Act: -0.1700
Data Index: 2990693 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9091. Min Range: -3.9091
Max Act: 3.4396. Min Act: -0.1700
Data Index: 6183656 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19