Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1230 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.8964. Min Act: -0.1700
Data Index: 2670792 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.8651. Min Act: -0.1700
Data Index: 451728 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.8651. Min Act: -0.1700
Data Index: 3911125 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.7714. Min Act: -0.1700
Data Index: 4314819 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.7714. Min Act: -0.1700
Data Index: 6013939 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.7714. Min Act: -0.1700
Data Index: 1997252 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.7401. Min Act: -0.1700
Data Index: 2360262 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6776. Min Act: -0.1700
Data Index: 2401802 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6776. Min Act: -0.1700
Data Index: 637053 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.7089. Min Act: -0.1700
Data Index: 3842945 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6464. Min Act: -0.1700
Data Index: 4852231 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6151. Min Act: -0.1700
Data Index: 482148 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6151. Min Act: -0.1700
Data Index: 1996123 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.6151. Min Act: -0.1700
Data Index: 7264821 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5839. Min Act: -0.1700
Data Index: 2084977 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5526. Min Act: -0.1700
Data Index: 7836717 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5214. Min Act: -0.1700
Data Index: 617303 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.4901. Min Act: -0.1700
Data Index: 8828620 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5214. Min Act: -0.1700
Data Index: 3853331 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8964. Min Range: -5.8964
Max Act: 5.5214. Min Act: -0.1700
Data Index: 1515966 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19