Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.5544. Min Act: -0.1700
Data Index: 4877335 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.2732. Min Act: -0.1700
Data Index: 3393619 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.2419. Min Act: -0.1700
Data Index: 5225415 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.2107. Min Act: -0.1700
Data Index: 153160 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.2107. Min Act: -0.1700
Data Index: 3296749 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.1169. Min Act: -0.1700
Data Index: 370672 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.0856. Min Act: -0.1700
Data Index: 2617449 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.0544. Min Act: -0.1700
Data Index: 3730004 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.0544. Min Act: -0.1700
Data Index: 4775326 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.0231. Min Act: -0.1700
Data Index: 1724495 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5544. Min Range: -4.5544
Max Act: 4.0231. Min Act: -0.1700
Data Index: 270857 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9606. Min Act: -0.1700
Data Index: 64237 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9293. Min Act: -0.1700
Data Index: 2204493 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9293. Min Act: -0.1700
Data Index: 7512260 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9293. Min Act: -0.1700
Data Index: 5402391 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9293. Min Act: -0.1700
Data Index: 3205013 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.9606. Min Act: -0.1700
Data Index: 5968749 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 7676462 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 5008525 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5544. Min Range: -4.5544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 4265357 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19