Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0868. Min Range: -6.0868
Max Act: 6.0868. Min Act: -0.1700
Data Index: 6574226 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.8368. Min Act: -0.1700
Data Index: 1686927 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.7743. Min Act: -0.1700
Data Index: 7443313 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.7431. Min Act: -0.1700
Data Index: 2299306 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.7118. Min Act: -0.1700
Data Index: 6550457 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.7118. Min Act: -0.1700
Data Index: 8655235 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.7118. Min Act: -0.1700
Data Index: 7773459 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1704567 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8052726 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.5556. Min Act: -0.1700
Data Index: 1145387 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4931. Min Act: -0.1700
Data Index: 3793428 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4931. Min Act: -0.1700
Data Index: 316584 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4618. Min Act: -0.1700
Data Index: 1657577 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4618. Min Act: -0.1700
Data Index: 4229639 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4618. Min Act: -0.1700
Data Index: 3241491 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4618. Min Act: -0.1700
Data Index: 6380663 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 7676372 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 1395124 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 199857 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0868. Min Range: -6.0868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 6433821 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19