Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8778. Min Act: -0.1700
Data Index: 7774027 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8778. Min Act: -0.1700
Data Index: 1274269 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8607. Min Act: -0.1700
Data Index: 313336 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8435. Min Act: -0.1700
Data Index: 4757906 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8435. Min Act: -0.1700
Data Index: 5885339 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 1022268 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 3568707 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 5981867 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8435. Min Act: -0.1700
Data Index: 5918777 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 1331210 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 5574550 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8264. Min Act: -0.1700
Data Index: 8170524 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 5073927 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 1267160 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 4158840 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.7920. Min Act: -0.1700
Data Index: 7367077 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 2938508 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.7920. Min Act: -0.1700
Data Index: 2322119 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 3439292 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8778. Min Range: -1.8778
Max Act: 1.8092. Min Act: -0.1700
Data Index: 4158354 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19