Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7429. Min Range: -7.7429
Max Act: 7.7429. Min Act: -0.1700
Data Index: 8139173 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7429. Min Range: -7.7429
Max Act: 7.6491. Min Act: -0.1700
Data Index: 3699600 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7429. Min Range: -7.7429
Max Act: 7.6179. Min Act: -0.1700
Data Index: 4479940 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7429. Min Range: -7.7429
Max Act: 7.2116. Min Act: -0.1700
Data Index: 5200621 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7429. Min Range: -7.7429
Max Act: 7.0554. Min Act: -0.1700
Data Index: 8710345 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.9929. Min Act: -0.1700
Data Index: 7768497 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.9616. Min Act: -0.1700
Data Index: 2843974 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.9616. Min Act: -0.1700
Data Index: 4594771 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.9616. Min Act: -0.1700
Data Index: 4127095 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.8991. Min Act: -0.1700
Data Index: 5885383 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.8679. Min Act: -0.1700
Data Index: 5785567 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.8679. Min Act: -0.1700
Data Index: 6584608 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.8366. Min Act: -0.1700
Data Index: 4111885 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.8054. Min Act: -0.1700
Data Index: 1517733 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.7429. Min Act: -0.1700
Data Index: 8245839 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.7429. Min Act: -0.1700
Data Index: 5730091 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.7429. Min Act: -0.1700
Data Index: 4638131 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.7116. Min Act: -0.1700
Data Index: 3581231 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.7116. Min Act: -0.1700
Data Index: 8345831 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7429. Min Range: -7.7429
Max Act: 6.6804. Min Act: -0.1700
Data Index: 3238416 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19