Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0104. Min Range: -8.0104
Max Act: 8.0104. Min Act: -0.1700
Data Index: 4322697 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.6667. Min Act: -0.1700
Data Index: 6793133 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.4792. Min Act: -0.1700
Data Index: 2242222 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.0729. Min Act: -0.1700
Data Index: 5536400 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.6354. Min Act: -0.1700
Data Index: 3867410 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.2604. Min Act: -0.1700
Data Index: 4480754 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.6667. Min Act: -0.1700
Data Index: 2106119 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.1354. Min Act: -0.1700
Data Index: 4161621 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.1354. Min Act: -0.1700
Data Index: 4643835 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0104. Min Range: -8.0104
Max Act: 5.2292. Min Act: -0.1700
Data Index: 5536215 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.8854. Min Act: -0.1700
Data Index: 6306660 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.8229. Min Act: -0.1700
Data Index: 7011323 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.7292. Min Act: -0.1700
Data Index: 1591954 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.7604. Min Act: -0.1700
Data Index: 5572276 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.2292. Min Act: -0.1700
Data Index: 6553911 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0104. Min Range: -8.0104
Max Act: 7.6354. Min Act: -0.1700
Data Index: 5597656 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.5104. Min Act: -0.1700
Data Index: 7812872 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.6354. Min Act: -0.1700
Data Index: 1130413 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0104. Min Range: -8.0104
Max Act: 6.7604. Min Act: -0.1700
Data Index: 2397077 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0104. Min Range: -8.0104
Max Act: 5.6354. Min Act: -0.1700
Data Index: 7009177 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19