Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.9577. Min Act: -0.1700
Data Index: 1067663 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.4577. Min Act: -0.1700
Data Index: 6528132 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.3327. Min Act: -0.1700
Data Index: 8182749 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.2077. Min Act: -0.1700
Data Index: 6423042 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.2077. Min Act: -0.1700
Data Index: 835119 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.0827. Min Act: -0.1700
Data Index: 818370 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.1452. Min Act: -0.1700
Data Index: 5556426 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.1452. Min Act: -0.1700
Data Index: 3000010 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.0202. Min Act: -0.1700
Data Index: 3425866 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.0827. Min Act: -0.1700
Data Index: 3962543 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.0827. Min Act: -0.1700
Data Index: 1318821 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9577. Min Range: -13.9577
Max Act: 13.0202. Min Act: -0.1700
Data Index: 7967430 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.8952. Min Act: -0.1700
Data Index: 835122 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.8327. Min Act: -0.1700
Data Index: 2257948 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.8952. Min Act: -0.1700
Data Index: 3551819 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.8327. Min Act: -0.1700
Data Index: 1069141 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.7702. Min Act: -0.1700
Data Index: 3357038 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.7702. Min Act: -0.1700
Data Index: 1499997 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.7077. Min Act: -0.1700
Data Index: 3999834 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9577. Min Range: -13.9577
Max Act: 12.7077. Min Act: -0.1700
Data Index: 4299662 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19