Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.6823. Min Act: -0.1700
Data Index: 5397932 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.6342. Min Act: -0.1700
Data Index: 1975142 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.6021. Min Act: -0.1700
Data Index: 8770186 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.6021. Min Act: -0.1700
Data Index: 6832824 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.6021. Min Act: -0.1700
Data Index: 6851889 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.5860. Min Act: -0.1700
Data Index: 630410 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.5214. Min Act: -0.1700
Data Index: 2403605 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.5052. Min Act: -0.1700
Data Index: 5466298 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.5214. Min Act: -0.1700
Data Index: 7213727 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4728. Min Act: -0.1700
Data Index: 8332111 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4728. Min Act: -0.1700
Data Index: 750516 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 6838521 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 4151322 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4728. Min Act: -0.1700
Data Index: 5360158 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4728. Min Act: -0.1700
Data Index: 1030403 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4403. Min Act: -0.1700
Data Index: 6011509 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 630411 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 122466 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 5822930 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6823. Min Range: -2.6823
Max Act: 2.4566. Min Act: -0.1700
Data Index: 2776174 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19