Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0484. Min Range: -7.0484
Max Act: 7.0484. Min Act: -0.1700
Data Index: 7470118 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.9546. Min Act: -0.1700
Data Index: 6294663 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.9546. Min Act: -0.1700
Data Index: 4368214 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8921. Min Act: -0.1700
Data Index: 7251535 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8921. Min Act: -0.1700
Data Index: 7150957 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8609. Min Act: -0.1700
Data Index: 6539575 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8609. Min Act: -0.1700
Data Index: 7410884 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8921. Min Act: -0.1700
Data Index: 3745313 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8609. Min Act: -0.1700
Data Index: 2849467 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8609. Min Act: -0.1700
Data Index: 6539974 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8296. Min Act: -0.1700
Data Index: 568523 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8296. Min Act: -0.1700
Data Index: 1687014 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8296. Min Act: -0.1700
Data Index: 7331729 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.8296. Min Act: -0.1700
Data Index: 3397588 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7984. Min Act: -0.1700
Data Index: 4253252 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7984. Min Act: -0.1700
Data Index: 3745314 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7984. Min Act: -0.1700
Data Index: 5751902 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1863983 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7984. Min Act: -0.1700
Data Index: 4025886 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0484. Min Range: -7.0484
Max Act: 6.7671. Min Act: -0.1700
Data Index: 6365039 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19