Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.7159. Min Act: -0.1700
Data Index: 1159127 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.6221. Min Act: -0.1700
Data Index: 7153454 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.5284. Min Act: -0.1700
Data Index: 4973964 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.5596. Min Act: -0.1700
Data Index: 2784294 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.4034. Min Act: -0.1700
Data Index: 7486348 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.4034. Min Act: -0.1700
Data Index: 4954476 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.4034. Min Act: -0.1700
Data Index: 1121732 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.4034. Min Act: -0.1700
Data Index: 2701979 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.3721. Min Act: -0.1700
Data Index: 6678753 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.3721. Min Act: -0.1700
Data Index: 3358883 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.3409. Min Act: -0.1700
Data Index: 2378189 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.3409. Min Act: -0.1700
Data Index: 6695464 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2784. Min Act: -0.1700
Data Index: 1121734 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.3096. Min Act: -0.1700
Data Index: 505985 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2471. Min Act: -0.1700
Data Index: 2629946 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2784. Min Act: -0.1700
Data Index: 5847976 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2784. Min Act: -0.1700
Data Index: 3681785 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2471. Min Act: -0.1700
Data Index: 247140 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2471. Min Act: -0.1700
Data Index: 5016337 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7159. Min Range: -5.7159
Max Act: 5.2471. Min Act: -0.1700
Data Index: 498543 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19