Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5352 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0730. Min Range: -9.0730
Max Act: 9.0730. Min Act: -0.1700
Data Index: 2277483 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.9480. Min Act: -0.1700
Data Index: 4433358 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.9480. Min Act: -0.1700
Data Index: 387364 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.8855. Min Act: -0.1700
Data Index: 387365 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.8230. Min Act: -0.1700
Data Index: 8670820 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.7605. Min Act: -0.1700
Data Index: 4729391 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.7605. Min Act: -0.1700
Data Index: 525812 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.6355. Min Act: -0.1700
Data Index: 1795013 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.6355. Min Act: -0.1700
Data Index: 5995275 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5105. Min Act: -0.1700
Data Index: 957796 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5105. Min Act: -0.1700
Data Index: 5040238 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5730. Min Act: -0.1700
Data Index: 1523318 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5105. Min Act: -0.1700
Data Index: 3824409 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5730. Min Act: -0.1700
Data Index: 4453523 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.5105. Min Act: -0.1700
Data Index: 2719626 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.4480. Min Act: -0.1700
Data Index: 8678612 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.4480. Min Act: -0.1700
Data Index: 6283707 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.4480. Min Act: -0.1700
Data Index: 3609088 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.4480. Min Act: -0.1700
Data Index: 5319810 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0730. Min Range: -9.0730
Max Act: 8.3855. Min Act: -0.1700
Data Index: 1187393 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19