Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0434. Min Range: -5.0434
Max Act: 5.0434. Min Act: -0.1700
Data Index: 8014494 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.8246. Min Act: -0.1700
Data Index: 951041 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.8246. Min Act: -0.1700
Data Index: 8214651 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.7621. Min Act: -0.1700
Data Index: 7843471 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.7309. Min Act: -0.1700
Data Index: 4176612 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.7309. Min Act: -0.1700
Data Index: 2337156 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.7621. Min Act: -0.1700
Data Index: 4948443 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6996. Min Act: -0.1700
Data Index: 2756260 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6996. Min Act: -0.1700
Data Index: 3441260 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6684. Min Act: -0.1700
Data Index: 958938 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6371. Min Act: -0.1700
Data Index: 1670748 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6371. Min Act: -0.1700
Data Index: 8527512 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6371. Min Act: -0.1700
Data Index: 7413290 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6371. Min Act: -0.1700
Data Index: 7578084 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.6059. Min Act: -0.1700
Data Index: 4014208 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.5434. Min Act: -0.1700
Data Index: 3362459 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.5746. Min Act: -0.1700
Data Index: 6430862 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.5434. Min Act: -0.1700
Data Index: 2839252 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.5121. Min Act: -0.1700
Data Index: 418044 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0434. Min Range: -5.0434
Max Act: 4.5121. Min Act: -0.1700
Data Index: 4636563 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19