Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.5550. Min Act: -0.1700
Data Index: 1213514 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.4416. Min Act: -0.1700
Data Index: 4547259 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3927. Min Act: -0.1700
Data Index: 688599 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3927. Min Act: -0.1700
Data Index: 7556265 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3927. Min Act: -0.1700
Data Index: 8736132 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 4806784 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 4834802 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 5829171 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3763. Min Act: -0.1700
Data Index: 6003343 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3763. Min Act: -0.1700
Data Index: 7498366 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 2752285 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3763. Min Act: -0.1700
Data Index: 646361 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 8042419 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3763. Min Act: -0.1700
Data Index: 2871585 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 1903150 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 683543 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3600. Min Act: -0.1700
Data Index: 520495 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3436. Min Act: -0.1700
Data Index: 1916787 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3436. Min Act: -0.1700
Data Index: 8285512 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5550. Min Range: -2.5550
Max Act: 2.3436. Min Act: -0.1700
Data Index: 4127632 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19