Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1016 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2681. Min Range: -6.2681
Max Act: 6.2681. Min Act: -0.1700
Data Index: 4382649 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.9243. Min Act: -0.1700
Data Index: 2131623 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.8931. Min Act: -0.1700
Data Index: 822827 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.7368. Min Act: -0.1700
Data Index: 3557752 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.7368. Min Act: -0.1700
Data Index: 3124443 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.7056. Min Act: -0.1700
Data Index: 5689631 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6743. Min Act: -0.1700
Data Index: 1468104 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6743. Min Act: -0.1700
Data Index: 6252914 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6743. Min Act: -0.1700
Data Index: 195421 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6431. Min Act: -0.1700
Data Index: 5530855 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6431. Min Act: -0.1700
Data Index: 2237508 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6431. Min Act: -0.1700
Data Index: 5765880 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6118. Min Act: -0.1700
Data Index: 8386806 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5806. Min Act: -0.1700
Data Index: 6352510 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5806. Min Act: -0.1700
Data Index: 829638 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5806. Min Act: -0.1700
Data Index: 7597901 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.6118. Min Act: -0.1700
Data Index: 3351901 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5493. Min Act: -0.1700
Data Index: 3981626 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5493. Min Act: -0.1700
Data Index: 7202073 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2681. Min Range: -6.2681
Max Act: 5.5493. Min Act: -0.1700
Data Index: 1573214 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19