Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.4739. Min Act: -0.1700
Data Index: 4210593 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.3506. Min Act: -0.1700
Data Index: 3113851 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.3154. Min Act: -0.1700
Data Index: 2482375 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2801. Min Act: -0.1700
Data Index: 46964 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2801. Min Act: -0.1700
Data Index: 5955762 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2801. Min Act: -0.1700
Data Index: 315552 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2801. Min Act: -0.1700
Data Index: 4210592 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2448. Min Act: -0.1700
Data Index: 4421525 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2448. Min Act: -0.1700
Data Index: 4395835 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2448. Min Act: -0.1700
Data Index: 1555505 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2448. Min Act: -0.1700
Data Index: 6042392 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2272. Min Act: -0.1700
Data Index: 2930864 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1693
Data Index: 6414208 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1700
Data Index: 6236750 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1700
Data Index: 1026402 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1700
Data Index: 7841653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1700
Data Index: 7572868 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.1744. Min Act: -0.1699
Data Index: 1811220 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.2096. Min Act: -0.1700
Data Index: 2364992 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4739. Min Range: -1.4739
Max Act: 1.1744. Min Act: -0.1697
Data Index: 558951 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19