Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.9024. Min Act: -0.1700
Data Index: 4193818 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.7149. Min Act: -0.1700
Data Index: 879664 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.6837. Min Act: -0.1700
Data Index: 387032 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.6837. Min Act: -0.1700
Data Index: 5870001 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.6524. Min Act: -0.1700
Data Index: 814961 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.6212. Min Act: -0.1700
Data Index: 1455015 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.5899. Min Act: -0.1700
Data Index: 2388372 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.5587. Min Act: -0.1700
Data Index: 5185903 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.5587. Min Act: -0.1700
Data Index: 3022527 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.5274. Min Act: -0.1700
Data Index: 7047443 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.5274. Min Act: -0.1700
Data Index: 8209808 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3618909 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4962. Min Act: -0.1700
Data Index: 3629906 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4962. Min Act: -0.1700
Data Index: 6608403 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4962. Min Act: -0.1700
Data Index: 5861147 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4962. Min Act: -0.1700
Data Index: 781823 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8365369 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8580958 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4628134 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9024. Min Range: -4.9024
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4945931 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19