Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.7509. Min Act: -0.1700
Data Index: 4120842 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6990. Min Act: -0.1700
Data Index: 6835908 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6555. Min Act: -0.1700
Data Index: 5197534 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6381. Min Act: -0.1700
Data Index: 2941983 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6032. Min Act: -0.1700
Data Index: 5783004 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5945. Min Act: -0.1700
Data Index: 3274493 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5858. Min Act: -0.1700
Data Index: 4466603 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5945. Min Act: -0.1700
Data Index: 3499760 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6032. Min Act: -0.1700
Data Index: 4323000 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.6032. Min Act: -0.1700
Data Index: 101290 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5858. Min Act: -0.1700
Data Index: 4585977 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5945. Min Act: -0.1700
Data Index: 186087 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5945. Min Act: -0.1700
Data Index: 8308432 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5945. Min Act: -0.1700
Data Index: 4454249 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5858. Min Act: -0.1700
Data Index: 2171948 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5858. Min Act: -0.1700
Data Index: 7826183 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5770. Min Act: -0.1700
Data Index: 871260 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5858. Min Act: -0.1700
Data Index: 496087 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5770. Min Act: -0.1700
Data Index: 6382976 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7509. Min Range: -1.7509
Max Act: 1.5770. Min Act: -0.1700
Data Index: 5122271 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19