Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0649. Min Range: -2.0649
Max Act: 2.0649. Min Act: -0.1700
Data Index: 8471596 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0649. Min Range: -2.0649
Max Act: 2.0481. Min Act: -0.1700
Data Index: 6927253 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0649. Min Range: -2.0649
Max Act: 2.0481. Min Act: -0.1700
Data Index: 6590125 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9975. Min Act: -0.1695
Data Index: 119435 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9975. Min Act: -0.1700
Data Index: 2367261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9806. Min Act: -0.1700
Data Index: 3396463 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9636. Min Act: -0.1700
Data Index: 3354177 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9636. Min Act: -0.1700
Data Index: 3562961 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9636. Min Act: -0.1700
Data Index: 6544811 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9636. Min Act: -0.1693
Data Index: 1170063 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9467. Min Act: -0.1700
Data Index: 7934022 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9636. Min Act: -0.1700
Data Index: 7934013 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9467. Min Act: -0.1700
Data Index: 4023032 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9297. Min Act: -0.1699
Data Index: 3491416 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9297. Min Act: -0.1700
Data Index: 2367271 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9212. Min Act: -0.1694
Data Index: 2277505 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9297. Min Act: -0.1700
Data Index: 432336 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9212. Min Act: -0.1699
Data Index: 8243129 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9212. Min Act: -0.1700
Data Index: 6726511 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0649. Min Range: -2.0649
Max Act: 1.9126. Min Act: -0.1700
Data Index: 4636581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19