Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.9970. Min Act: -0.1700
Data Index: 3946250 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.8095. Min Act: -0.1700
Data Index: 6513309 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.6845. Min Act: -0.1700
Data Index: 7727326 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.5595. Min Act: -0.1700
Data Index: 6218521 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.4970. Min Act: -0.1700
Data Index: 6412076 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.4033. Min Act: -0.1700
Data Index: 7509186 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.3720. Min Act: -0.1700
Data Index: 3486417 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2783. Min Act: -0.1700
Data Index: 8395637 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2783. Min Act: -0.1700
Data Index: 4551613 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2783. Min Act: -0.1700
Data Index: 4360135 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.3095. Min Act: -0.1700
Data Index: 4589598 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2158. Min Act: -0.1700
Data Index: 4486321 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2158. Min Act: -0.1700
Data Index: 3436523 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.2158. Min Act: -0.1700
Data Index: 4858395 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1845. Min Act: -0.1700
Data Index: 663205 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1845. Min Act: -0.1700
Data Index: 7385715 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1845. Min Act: -0.1700
Data Index: 6298666 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1533. Min Act: -0.1700
Data Index: 8055375 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1533. Min Act: -0.1700
Data Index: 7525807 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9970. Min Range: -7.9970
Max Act: 7.1533. Min Act: -0.1700
Data Index: 4256453 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19