Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.3993. Min Act: -0.1700
Data Index: 176698 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.2743. Min Act: -0.1700
Data Index: 3488854 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.1805. Min Act: -0.1700
Data Index: 2426997 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.1805. Min Act: -0.1700
Data Index: 6470508 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.1493. Min Act: -0.1700
Data Index: 1388757 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.1180. Min Act: -0.1700
Data Index: 6848215 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.0243. Min Act: -0.1700
Data Index: 493771 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3993. Min Range: -4.3993
Max Act: 4.0243. Min Act: -0.1700
Data Index: 2792634 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9930. Min Act: -0.1700
Data Index: 8330769 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9930. Min Act: -0.1700
Data Index: 8815515 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9930. Min Act: -0.1700
Data Index: 104838 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 7642449 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9930. Min Act: -0.1700
Data Index: 1413696 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 3483118 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 2291242 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 4902699 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 2296949 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 3891005 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9617. Min Act: -0.1700
Data Index: 211169 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3993. Min Range: -4.3993
Max Act: 3.9305. Min Act: -0.1700
Data Index: 7148831 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19