Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 142 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.5031. Min Range: -14.5031
Max Act: 14.5031. Min Act: -0.1700
Data Index: 590029 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5031. Min Range: -14.5031
Max Act: 14.0656. Min Act: -0.1700
Data Index: 1804641 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.9406. Min Act: -0.1700
Data Index: 6941376 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.7531. Min Act: -0.1700
Data Index: 6506214 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.6906. Min Act: -0.1700
Data Index: 5905247 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.6281. Min Act: -0.1700
Data Index: 6049409 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.6281. Min Act: -0.1700
Data Index: 2442342 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.5031. Min Act: -0.1700
Data Index: 4845811 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.5031. Min Act: -0.1700
Data Index: 8311254 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 6265704 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 1821625 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 2603962 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 1178705 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 3418215 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.3781. Min Act: -0.1700
Data Index: 4279249 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.4406. Min Act: -0.1700
Data Index: 5546274 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.3781. Min Act: -0.1700
Data Index: 7479906 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.3156. Min Act: -0.1700
Data Index: 5124383 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.3781. Min Act: -0.1700
Data Index: 2781575 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5031. Min Range: -14.5031
Max Act: 13.3781. Min Act: -0.1700
Data Index: 1515060 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19