Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 159 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.9040. Min Act: -0.1700
Data Index: 1779081 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8870. Min Act: -0.1700
Data Index: 3925262 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8870. Min Act: -0.1700
Data Index: 8684561 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8613. Min Act: -0.1700
Data Index: 7074438 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8528. Min Act: -0.1700
Data Index: 975994 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8442. Min Act: -0.1700
Data Index: 4555450 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8356. Min Act: -0.1700
Data Index: 3824024 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8185. Min Act: -0.1700
Data Index: 5789738 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8442. Min Act: -0.1700
Data Index: 4159168 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8271. Min Act: -0.1700
Data Index: 3647751 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8356. Min Act: -0.1700
Data Index: 8798068 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8013. Min Act: -0.1700
Data Index: 104262 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8185. Min Act: -0.1700
Data Index: 1710683 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8099. Min Act: -0.1700
Data Index: 5405060 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8013. Min Act: -0.1700
Data Index: 1276520 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8099. Min Act: -0.1700
Data Index: 3290233 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8099. Min Act: -0.1698
Data Index: 6477922 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8013. Min Act: -0.1700
Data Index: 6820829 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8099. Min Act: -0.1700
Data Index: 104263 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9040. Min Range: -1.9040
Max Act: 1.8013. Min Act: -0.1700
Data Index: 7190093 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19