Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1539. Min Act: -0.1700
Data Index: 3971334 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1539. Min Act: -0.1700
Data Index: 5219532 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6879435 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 3625232 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 8439558 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 3205259 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 2848079 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 8243009 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 8219805 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 1090553 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6659371 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6620574 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 2657707 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6514849 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6179337 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 1395889 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.1227. Min Act: -0.1700
Data Index: 4679635 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 3276247 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 3287349 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1539. Min Range: -5.1539
Max Act: 5.0914. Min Act: -0.1700
Data Index: 27121 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19