Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.5168. Min Act: -0.1700
Data Index: 3918063 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.2668. Min Act: -0.1700
Data Index: 120410 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.0793. Min Act: -0.1700
Data Index: 884832 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.0793. Min Act: -0.1700
Data Index: 8431455 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.0168. Min Act: -0.1700
Data Index: 3331843 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5168. Min Range: -8.5168
Max Act: 8.0168. Min Act: -0.1700
Data Index: 6143561 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8918. Min Act: -0.1700
Data Index: 3041287 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.9543. Min Act: -0.1700
Data Index: 5800119 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8918. Min Act: -0.1700
Data Index: 4963217 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8918. Min Act: -0.1700
Data Index: 2952124 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8293. Min Act: -0.1700
Data Index: 599945 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8293. Min Act: -0.1700
Data Index: 2615814 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8293. Min Act: -0.1700
Data Index: 4957979 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.8293. Min Act: -0.1700
Data Index: 4762449 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7668. Min Act: -0.1700
Data Index: 8513559 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7668. Min Act: -0.1700
Data Index: 1747382 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7043. Min Act: -0.1700
Data Index: 7901847 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7668. Min Act: -0.1700
Data Index: 1313010 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7668. Min Act: -0.1700
Data Index: 7417601 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5168. Min Range: -8.5168
Max Act: 7.7043. Min Act: -0.1700
Data Index: 4066680 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19