Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1875. Min Range: -10.1875
Max Act: 10.1875. Min Act: -0.1700
Data Index: 3996846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1875. Min Range: -10.1875
Max Act: 10.1250. Min Act: -0.1700
Data Index: 3494510 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1875. Min Range: -10.1875
Max Act: 10.0000. Min Act: -0.1700
Data Index: 588579 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.7500. Min Act: -0.1700
Data Index: 5078113 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.6875. Min Act: -0.1700
Data Index: 3996847 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.6250. Min Act: -0.1700
Data Index: 5202782 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.5000. Min Act: -0.1700
Data Index: 205581 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.5000. Min Act: -0.1700
Data Index: 4415502 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.5000. Min Act: -0.1700
Data Index: 4415489 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.4375. Min Act: -0.1700
Data Index: 2538233 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.4375. Min Act: -0.1700
Data Index: 4039730 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.3750. Min Act: -0.1700
Data Index: 8781147 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.3750. Min Act: -0.1700
Data Index: 1028855 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.4375. Min Act: -0.1700
Data Index: 3647337 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.3125. Min Act: -0.1698
Data Index: 5966894 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.1875. Min Act: -0.1700
Data Index: 1028857 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.2500. Min Act: -0.1700
Data Index: 7165416 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.1875. Min Act: -0.1700
Data Index: 638565 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.1875. Min Act: -0.1700
Data Index: 2746203 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1875. Min Range: -10.1875
Max Act: 9.1875. Min Act: -0.1700
Data Index: 5287981 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19