Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5667 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0431. Min Range: -5.0431
Max Act: 5.0431. Min Act: -0.1700
Data Index: 8130583 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0431. Min Range: -5.0431
Max Act: 5.0118. Min Act: -0.1700
Data Index: 8529516 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.9493. Min Act: -0.1700
Data Index: 5337679 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.9181. Min Act: -0.1700
Data Index: 5971752 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.9181. Min Act: -0.1700
Data Index: 5081787 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8868. Min Act: -0.1700
Data Index: 487267 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8868. Min Act: -0.1700
Data Index: 8660816 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8868. Min Act: -0.1700
Data Index: 487262 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8243. Min Act: -0.1700
Data Index: 5942337 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2758628 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2120972 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 135114 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4064242 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2120971 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8556. Min Act: -0.1700
Data Index: 84321 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8243. Min Act: -0.1700
Data Index: 4073077 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8243. Min Act: -0.1700
Data Index: 487272 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8243. Min Act: -0.1700
Data Index: 5483532 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.8243. Min Act: -0.1700
Data Index: 5739306 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0431. Min Range: -5.0431
Max Act: 4.7931. Min Act: -0.1700
Data Index: 4076916 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19