Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.7869. Min Act: -0.1528
Data Index: 4362674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.7438. Min Act: -0.1700
Data Index: 266978 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.7352. Min Act: -0.1700
Data Index: 8827478 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.7265. Min Act: -0.1700
Data Index: 2884480 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.7179. Min Act: -0.1697
Data Index: 6720100 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6832. Min Act: -0.1699
Data Index: 7207169 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6918. Min Act: -0.1700
Data Index: 717488 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6832. Min Act: -0.1700
Data Index: 3139684 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6832. Min Act: -0.1700
Data Index: 8201183 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6832. Min Act: -0.1700
Data Index: 1416238 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6571. Min Act: -0.1700
Data Index: 7168386 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6745. Min Act: -0.1700
Data Index: 4696537 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6571. Min Act: -0.1700
Data Index: 6269649 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6484. Min Act: -0.1700
Data Index: 564024 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6484. Min Act: -0.1700
Data Index: 3885846 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6397. Min Act: -0.1700
Data Index: 7325593 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6310. Min Act: -0.1700
Data Index: 4960282 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6397. Min Act: -0.1700
Data Index: 6548323 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6310. Min Act: -0.1700
Data Index: 3885853 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7869. Min Range: -1.7869
Max Act: 1.6397. Min Act: -0.1700
Data Index: 5469509 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19