Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0365. Min Range: -12.0365
Max Act: 12.0365. Min Act: -0.1700
Data Index: 857026 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.6615. Min Act: -0.1700
Data Index: 2830161 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.5365. Min Act: -0.1700
Data Index: 2807709 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.5365. Min Act: -0.1700
Data Index: 1062607 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.5365. Min Act: -0.1700
Data Index: 1727905 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.4115. Min Act: -0.1700
Data Index: 5966145 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.4115. Min Act: -0.1700
Data Index: 1135915 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.4115. Min Act: -0.1700
Data Index: 5216302 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.4115. Min Act: -0.1700
Data Index: 8225244 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.4115. Min Act: -0.1700
Data Index: 7077343 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 1649777 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 4829349 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 6472580 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 917092 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 1055301 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.3490. Min Act: -0.1700
Data Index: 6732776 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.2865. Min Act: -0.1700
Data Index: 5234139 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.2240. Min Act: -0.1700
Data Index: 4714035 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.2865. Min Act: -0.1700
Data Index: 8663228 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0365. Min Range: -12.0365
Max Act: 11.2240. Min Act: -0.1700
Data Index: 827537 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19