Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.3775. Min Act: -0.1700
Data Index: 4533444 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.3462. Min Act: -0.1700
Data Index: 7700255 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.2837. Min Act: -0.1700
Data Index: 6554019 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1900. Min Act: -0.1700
Data Index: 2308014 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6198732 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0962. Min Act: -0.1700
Data Index: 5945441 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1275. Min Act: -0.1700
Data Index: 4465495 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4998212 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5737239 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6348981 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0962. Min Act: -0.1700
Data Index: 3364760 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 5039965 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0650. Min Act: -0.1700
Data Index: 2675191 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 5146031 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2387835 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 1454254 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7202944 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0337. Min Act: -0.1700
Data Index: 361326 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0025. Min Act: -0.1700
Data Index: 658812 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3775. Min Range: -5.3775
Max Act: 5.0025. Min Act: -0.1700
Data Index: 4959215 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19