Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.5278. Min Act: -0.1700
Data Index: 1080547 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.4966. Min Act: -0.1700
Data Index: 7008287 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.4028. Min Act: -0.1700
Data Index: 119294 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.3716. Min Act: -0.1700
Data Index: 696645 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.3403. Min Act: -0.1700
Data Index: 8986 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.3091. Min Act: -0.1700
Data Index: 1708795 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.2778. Min Act: -0.1700
Data Index: 715806 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.2778. Min Act: -0.1700
Data Index: 7744747 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.2466. Min Act: -0.1700
Data Index: 5079927 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.2153. Min Act: -0.1700
Data Index: 322029 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.1841. Min Act: -0.1700
Data Index: 441663 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.1528. Min Act: -0.1700
Data Index: 8322618 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.1528. Min Act: -0.1700
Data Index: 4494776 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0903. Min Act: -0.1700
Data Index: 3937000 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0903. Min Act: -0.1700
Data Index: 7006093 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0903. Min Act: -0.1700
Data Index: 2225186 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0903. Min Act: -0.1700
Data Index: 5793502 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0591. Min Act: -0.1700
Data Index: 4722193 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0591. Min Act: -0.1700
Data Index: 6929473 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5278. Min Range: -7.5278
Max Act: 7.0278. Min Act: -0.1700
Data Index: 6972184 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19