Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 248 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8331. Min Act: -0.1700
Data Index: 4109774 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8245. Min Act: -0.1700
Data Index: 7495446 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8331. Min Act: -0.1696
Data Index: 5740251 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8159. Min Act: -0.1700
Data Index: 6164279 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7987. Min Act: -0.1700
Data Index: 4252994 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8073. Min Act: -0.1698
Data Index: 7495448 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7987. Min Act: -0.1700
Data Index: 1185040 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8073. Min Act: -0.1700
Data Index: 8739915 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7987. Min Act: -0.1700
Data Index: 7855550 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.8073. Min Act: -0.1700
Data Index: 7664829 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7901. Min Act: -0.1700
Data Index: 7176304 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7643. Min Act: -0.1697
Data Index: 6253183 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7815. Min Act: -0.1700
Data Index: 5797345 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7557. Min Act: -0.1700
Data Index: 8747971 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7557. Min Act: -0.1700
Data Index: 6946895 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7643. Min Act: -0.1700
Data Index: 8747959 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7643. Min Act: -0.1700
Data Index: 1207751 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7557. Min Act: -0.1700
Data Index: 2440301 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7557. Min Act: -0.1700
Data Index: 7287118 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8331. Min Range: -1.8331
Max Act: 1.7643. Min Act: -0.1700
Data Index: 5851318 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19