Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.9156. Min Act: -0.1700
Data Index: 208991 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.7906. Min Act: -0.1700
Data Index: 5941416 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.7593. Min Act: -0.1700
Data Index: 6763102 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.7281. Min Act: -0.1700
Data Index: 7537527 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 3669035 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 6601657 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 2526598 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 4110159 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 2941637 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 5986778 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 5986785 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5718. Min Act: -0.1700
Data Index: 5640962 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5718. Min Act: -0.1700
Data Index: 6424791 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5718. Min Act: -0.1700
Data Index: 3917065 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 1851641 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5718. Min Act: -0.1700
Data Index: 5480989 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 977058 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5406. Min Act: -0.1700
Data Index: 534174 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5093. Min Act: -0.1700
Data Index: 1458559 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5093. Min Act: -0.1700
Data Index: 5901919 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19