Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1372. Min Range: -8.1372
Max Act: 8.0122. Min Act: -0.1700
Data Index: 3167353 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1372. Min Range: -8.1372
Max Act: 8.0747. Min Act: -0.1700
Data Index: 2657194 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1372. Min Range: -8.1372
Max Act: 8.0122. Min Act: -0.1700
Data Index: 5831590 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1372. Min Range: -8.1372
Max Act: 8.1372. Min Act: -0.1700
Data Index: 1007140 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 3167348 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1372. Min Range: -8.1372
Max Act: 8.0122. Min Act: -0.1700
Data Index: 5831585 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 3167349 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 5716678 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 5831586 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 2657190 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8247. Min Act: -0.1700
Data Index: 1007145 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8247. Min Act: -0.1700
Data Index: 5716679 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.8872. Min Act: -0.1700
Data Index: 5716674 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.7622. Min Act: -0.1700
Data Index: 1007144 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.7622. Min Act: -0.1700
Data Index: 2657189 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.3872. Min Act: -0.1700
Data Index: 3447207 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1372. Min Range: -8.1372
Max Act: 7.1060. Min Act: -0.1700
Data Index: 3830776 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1372. Min Range: -8.1372
Max Act: 6.9810. Min Act: -0.1700
Data Index: 6214478 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1372. Min Range: -8.1372
Max Act: 6.9810. Min Act: -0.1700
Data Index: 1282080 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1372. Min Range: -8.1372
Max Act: 6.7935. Min Act: -0.1700
Data Index: 385312 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19