Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6121 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3369976 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.8722. Min Act: -0.1700
Data Index: 5244302 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.8097. Min Act: -0.1700
Data Index: 6387698 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.8097. Min Act: -0.1700
Data Index: 7576724 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.7472. Min Act: -0.1700
Data Index: 3892922 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6847. Min Act: -0.1700
Data Index: 964512 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6534. Min Act: -0.1700
Data Index: 6626513 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6534. Min Act: -0.1700
Data Index: 7674455 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6534. Min Act: -0.1700
Data Index: 7193284 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6847. Min Act: -0.1700
Data Index: 4126042 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6222. Min Act: -0.1700
Data Index: 2835099 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6222. Min Act: -0.1700
Data Index: 7630752 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6222. Min Act: -0.1700
Data Index: 268148 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.6222. Min Act: -0.1700
Data Index: 455459 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5909. Min Act: -0.1700
Data Index: 4795522 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5909. Min Act: -0.1700
Data Index: 5133567 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5909. Min Act: -0.1700
Data Index: 7007588 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5909. Min Act: -0.1700
Data Index: 7722094 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5597. Min Act: -0.1700
Data Index: 3822613 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9034. Min Range: -5.9034
Max Act: 5.5597. Min Act: -0.1700
Data Index: 1311129 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19