Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1131 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.2588. Min Act: -0.1700
Data Index: 2798179 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.2901. Min Act: -0.1700
Data Index: 8169169 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.1338. Min Act: -0.1700
Data Index: 4273000 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.1026. Min Act: -0.1700
Data Index: 528419 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.0401. Min Act: -0.1700
Data Index: 8129155 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.0401. Min Act: -0.1700
Data Index: 6531656 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.0401. Min Act: -0.1700
Data Index: 436985 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2901. Min Range: -6.2901
Max Act: 6.0088. Min Act: -0.1700
Data Index: 7019534 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.9776. Min Act: -0.1700
Data Index: 8661252 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.9463. Min Act: -0.1700
Data Index: 8809550 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.9151. Min Act: -0.1700
Data Index: 1551580 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.9463. Min Act: -0.1700
Data Index: 8397119 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8838. Min Act: -0.1700
Data Index: 7944920 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8838. Min Act: -0.1700
Data Index: 8245700 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8838. Min Act: -0.1700
Data Index: 3627219 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5001411 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8526. Min Act: -0.1700
Data Index: 2178406 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8526. Min Act: -0.1700
Data Index: 8262842 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8213. Min Act: -0.1700
Data Index: 8600324 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2901. Min Range: -6.2901
Max Act: 5.8526. Min Act: -0.1700
Data Index: 3732984 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19