Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0365. Min Range: -7.0365
Max Act: 7.0365. Min Act: -0.1700
Data Index: 4588413 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.8177. Min Act: -0.1700
Data Index: 8470650 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.7865. Min Act: -0.1700
Data Index: 7687534 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.7240. Min Act: -0.1700
Data Index: 5457475 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.7240. Min Act: -0.1700
Data Index: 8515191 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.6927. Min Act: -0.1700
Data Index: 1081528 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.5990. Min Act: -0.1700
Data Index: 1251662 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.5990. Min Act: -0.1700
Data Index: 324209 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.5990. Min Act: -0.1700
Data Index: 1088448 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.5990. Min Act: -0.1700
Data Index: 7729651 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4740. Min Act: -0.1700
Data Index: 4515379 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.5052. Min Act: -0.1700
Data Index: 4594238 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4740. Min Act: -0.1700
Data Index: 6959709 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4427. Min Act: -0.1700
Data Index: 3585715 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4427. Min Act: -0.1700
Data Index: 5780225 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4740. Min Act: -0.1700
Data Index: 1825446 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.4115. Min Act: -0.1700
Data Index: 6977982 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3793826 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.3802. Min Act: -0.1700
Data Index: 1088453 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0365. Min Range: -7.0365
Max Act: 6.3490. Min Act: -0.1700
Data Index: 5162022 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19