Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.6927. Min Act: -0.1700
Data Index: 8567189 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.6301. Min Act: -0.1700
Data Index: 6396747 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5831. Min Act: -0.1700
Data Index: 6867209 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5831. Min Act: -0.1700
Data Index: 5653546 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5675. Min Act: -0.1700
Data Index: 4057361 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5518. Min Act: -0.1700
Data Index: 7352647 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 3122074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5518. Min Act: -0.1700
Data Index: 4829336 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 5902580 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 3363801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5362. Min Act: -0.1700
Data Index: 5504352 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5049. Min Act: -0.1700
Data Index: 7186456 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 2039936 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 7177429 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.4892. Min Act: -0.1700
Data Index: 4543661 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5049. Min Act: -0.1700
Data Index: 7983130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.5205. Min Act: -0.1700
Data Index: 5991354 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.4735. Min Act: -0.1700
Data Index: 5164837 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.4735. Min Act: -0.1700
Data Index: 6937025 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6927. Min Range: -3.6927
Max Act: 3.4422. Min Act: -0.1700
Data Index: 7525052 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19