Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.5932. Min Act: -0.1700
Data Index: 177075 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.6244. Min Act: -0.1700
Data Index: 209230 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.5307. Min Act: -0.1700
Data Index: 622946 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4634238 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4994. Min Act: -0.1700
Data Index: 8204368 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4994. Min Act: -0.1700
Data Index: 5336956 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4682. Min Act: -0.1700
Data Index: 4305274 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4682. Min Act: -0.1700
Data Index: 6822620 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4682. Min Act: -0.1700
Data Index: 1866950 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4682. Min Act: -0.1700
Data Index: 5289079 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4682. Min Act: -0.1700
Data Index: 5450168 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4369. Min Act: -0.1700
Data Index: 3494540 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4369. Min Act: -0.1700
Data Index: 633810 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4369. Min Act: -0.1700
Data Index: 5366596 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4369. Min Act: -0.1700
Data Index: 6462526 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4057. Min Act: -0.1700
Data Index: 738181 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.4057. Min Act: -0.1700
Data Index: 4600534 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.3744. Min Act: -0.1700
Data Index: 2282837 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.3744. Min Act: -0.1700
Data Index: 1845931 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6244. Min Range: -4.6244
Max Act: 4.3744. Min Act: -0.1700
Data Index: 4195357 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19