Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4659. Min Act: -0.1700
Data Index: 4682722 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4189. Min Act: -0.1700
Data Index: 5864373 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3719. Min Act: -0.1700
Data Index: 4844993 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.4033. Min Act: -0.1700
Data Index: 6248351 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3562. Min Act: -0.1700
Data Index: 1640252 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3562. Min Act: -0.1700
Data Index: 4208706 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3091. Min Act: -0.1700
Data Index: 4523938 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3248. Min Act: -0.1700
Data Index: 574898 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3405. Min Act: -0.1700
Data Index: 2841236 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3405. Min Act: -0.1700
Data Index: 1395909 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3562. Min Act: -0.1700
Data Index: 213475 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3091. Min Act: -0.1700
Data Index: 5075829 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3091. Min Act: -0.1700
Data Index: 7847304 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3248. Min Act: -0.1700
Data Index: 2693912 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.3091. Min Act: -0.1700
Data Index: 6082389 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.2934. Min Act: -0.1700
Data Index: 6819065 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.2934. Min Act: -0.1700
Data Index: 2507992 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.2777. Min Act: -0.1700
Data Index: 5867335 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.2777. Min Act: -0.1700
Data Index: 1562673 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4659. Min Range: -3.4659
Max Act: 3.2463. Min Act: -0.1700
Data Index: 1588523 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19