Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3860 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.4540. Min Act: -0.1700
Data Index: 3309763 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.3290. Min Act: -0.1700
Data Index: 1074913 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.2665. Min Act: -0.1700
Data Index: 5171399 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.0790. Min Act: -0.1700
Data Index: 5522120 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.0478. Min Act: -0.1700
Data Index: 6367171 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4540. Min Range: -6.4540
Max Act: 6.0165. Min Act: -0.1700
Data Index: 6460380 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.8915. Min Act: -0.1700
Data Index: 7894274 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7978. Min Act: -0.1700
Data Index: 1031708 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7665. Min Act: -0.1700
Data Index: 603020 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7665. Min Act: -0.1700
Data Index: 747900 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7665. Min Act: -0.1700
Data Index: 2153170 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5479791 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5808252 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7353. Min Act: -0.1700
Data Index: 263421 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7040. Min Act: -0.1700
Data Index: 4038651 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7040. Min Act: -0.1700
Data Index: 2959908 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.7040. Min Act: -0.1700
Data Index: 4865731 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.6728. Min Act: -0.1700
Data Index: 3864263 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.6728. Min Act: -0.1700
Data Index: 3483986 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4540. Min Range: -6.4540
Max Act: 5.6728. Min Act: -0.1700
Data Index: 4558328 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19