Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5518. Min Range: -7.5518
Max Act: 7.5518. Min Act: -0.1700
Data Index: 8776915 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5518. Min Range: -7.5518
Max Act: 7.1768. Min Act: -0.1700
Data Index: 755112 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5518. Min Range: -7.5518
Max Act: 7.1143. Min Act: -0.1700
Data Index: 6660641 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.9581. Min Act: -0.1700
Data Index: 3047943 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.8956. Min Act: -0.1700
Data Index: 8161039 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.9268. Min Act: -0.1700
Data Index: 7127206 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.9268. Min Act: -0.1700
Data Index: 1404581 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.8956. Min Act: -0.1700
Data Index: 152465 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.8331. Min Act: -0.1700
Data Index: 1334771 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.8331. Min Act: -0.1700
Data Index: 4329108 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.8018. Min Act: -0.1700
Data Index: 1663077 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 6863748 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.7393. Min Act: -0.1700
Data Index: 6128626 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.7081. Min Act: -0.1700
Data Index: 1504274 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.6768. Min Act: -0.1700
Data Index: 1419575 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.6768. Min Act: -0.1700
Data Index: 4013997 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.6768. Min Act: -0.1700
Data Index: 5337783 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.6143. Min Act: -0.1700
Data Index: 1797350 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.6143. Min Act: -0.1700
Data Index: 3481649 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5518. Min Range: -7.5518
Max Act: 6.5831. Min Act: -0.1700
Data Index: 637266 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19