Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 5049586 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1404. Min Act: -0.1700
Data Index: 209882 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0932. Min Act: -0.1700
Data Index: 6573156 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0774. Min Act: -0.1700
Data Index: 7155556 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0616. Min Act: -0.1700
Data Index: 1192248 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 7964458 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 5634784 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0616. Min Act: -0.1700
Data Index: 2898020 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 1808075 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 1200979 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 8015387 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0459. Min Act: -0.1700
Data Index: 1820457 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 7220594 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 8452559 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0301. Min Act: -0.1700
Data Index: 2870954 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0143. Min Act: -0.1700
Data Index: 2870953 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0143. Min Act: -0.1700
Data Index: 8012472 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0143. Min Act: -0.1700
Data Index: 1558460 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0143. Min Act: -0.1700
Data Index: 1969216 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.9985. Min Act: -0.1700
Data Index: 6510943 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19