Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5071 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.6681. Min Act: -0.1700
Data Index: 7367414 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.6056. Min Act: -0.1700
Data Index: 6660198 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.4181. Min Act: -0.1700
Data Index: 7871772 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.2619. Min Act: -0.1700
Data Index: 4924706 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.2306. Min Act: -0.1700
Data Index: 8106124 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.2306. Min Act: -0.1700
Data Index: 4804711 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1994. Min Act: -0.1700
Data Index: 4313362 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1994. Min Act: -0.1700
Data Index: 7348775 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1994. Min Act: -0.1700
Data Index: 7859968 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1056. Min Act: -0.1700
Data Index: 482827 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1056. Min Act: -0.1700
Data Index: 5508975 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.1369. Min Act: -0.1700
Data Index: 7030355 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0744. Min Act: -0.1700
Data Index: 4392743 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0744. Min Act: -0.1700
Data Index: 7070697 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0744. Min Act: -0.1700
Data Index: 8350395 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0744. Min Act: -0.1700
Data Index: 7394777 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 6711674 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 8647703 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1879575 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6681. Min Range: -5.6681
Max Act: 5.0119. Min Act: -0.1700
Data Index: 5951936 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19