Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1518 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3257. Min Range: -9.3257
Max Act: 9.3257. Min Act: -0.1700
Data Index: 6114318 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3257. Min Range: -9.3257
Max Act: 9.2007. Min Act: -0.1700
Data Index: 8363373 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.8882. Min Act: -0.1700
Data Index: 8363366 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.7632. Min Act: -0.1700
Data Index: 8363376 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.7007. Min Act: -0.1700
Data Index: 6339711 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.7007. Min Act: -0.1700
Data Index: 1825808 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.7007. Min Act: -0.1700
Data Index: 3243057 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.7632. Min Act: -0.1700
Data Index: 8363378 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.6382. Min Act: -0.1700
Data Index: 2767207 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.6382. Min Act: -0.1700
Data Index: 8363379 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5757. Min Act: -0.1700
Data Index: 7652389 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5757. Min Act: -0.1700
Data Index: 1315952 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5757. Min Act: -0.1700
Data Index: 4916234 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5132. Min Act: -0.1700
Data Index: 7686475 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5132. Min Act: -0.1700
Data Index: 3933070 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5132. Min Act: -0.1700
Data Index: 2428470 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5757. Min Act: -0.1700
Data Index: 8392309 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.5132. Min Act: -0.1700
Data Index: 4362740 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.3882. Min Act: -0.1700
Data Index: 4409349 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3257. Min Range: -9.3257
Max Act: 8.4507. Min Act: -0.1700
Data Index: 1153155 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19