Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.9701. Min Act: -0.1700
Data Index: 7389895 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.8451. Min Act: -0.1700
Data Index: 5057065 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.8138. Min Act: -0.1700
Data Index: 6513207 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.7513. Min Act: -0.1700
Data Index: 1067456 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.7201. Min Act: -0.1700
Data Index: 559765 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.7201. Min Act: -0.1700
Data Index: 5581538 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.7201. Min Act: -0.1700
Data Index: 4989861 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.7201. Min Act: -0.1700
Data Index: 6171323 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6888. Min Act: -0.1700
Data Index: 8511448 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6576. Min Act: -0.1700
Data Index: 8617630 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6576. Min Act: -0.1700
Data Index: 5901605 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6576. Min Act: -0.1700
Data Index: 1170600 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6576. Min Act: -0.1700
Data Index: 5302591 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.6263. Min Act: -0.1700
Data Index: 834285 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6755282 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5951. Min Act: -0.1700
Data Index: 735510 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6996491 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5951. Min Act: -0.1700
Data Index: 5735975 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5951. Min Act: -0.1700
Data Index: 5225538 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9701. Min Range: -5.9701
Max Act: 5.5638. Min Act: -0.1700
Data Index: 6008490 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19