Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3107. Min Range: -5.3107
Max Act: 5.3107. Min Act: -0.1700
Data Index: 6457048 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.9044. Min Act: -0.1700
Data Index: 8435563 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.6857. Min Act: -0.1700
Data Index: 3216229 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.6544. Min Act: -0.1700
Data Index: 3933697 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5919. Min Act: -0.1700
Data Index: 4088770 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5607. Min Act: -0.1700
Data Index: 3373691 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5607. Min Act: -0.1700
Data Index: 3134233 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5607. Min Act: -0.1700
Data Index: 2232764 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5607. Min Act: -0.1700
Data Index: 7109727 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5294. Min Act: -0.1700
Data Index: 4942997 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 8103761 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.5294. Min Act: -0.1700
Data Index: 6834595 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4982. Min Act: -0.1700
Data Index: 2572854 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 183959 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 8263476 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 2268246 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 7814580 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4669. Min Act: -0.1700
Data Index: 470076 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4357. Min Act: -0.1700
Data Index: 6136982 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3107. Min Range: -5.3107
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5559885 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19