Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5170. Min Range: -7.5170
Max Act: 7.5170. Min Act: -0.1700
Data Index: 2927225 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5170. Min Range: -7.5170
Max Act: 7.1420. Min Act: -0.1700
Data Index: 1814662 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5170. Min Range: -7.5170
Max Act: 7.0170. Min Act: -0.1700
Data Index: 1803906 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.8607. Min Act: -0.1700
Data Index: 7120785 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.8607. Min Act: -0.1700
Data Index: 8118734 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.8295. Min Act: -0.1700
Data Index: 8422360 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.7357. Min Act: -0.1700
Data Index: 7340717 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6732. Min Act: -0.1700
Data Index: 5902112 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6107. Min Act: -0.1700
Data Index: 3344721 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6420. Min Act: -0.1700
Data Index: 6707563 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6107. Min Act: -0.1700
Data Index: 7337539 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6107. Min Act: -0.1700
Data Index: 4218902 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.6107. Min Act: -0.1700
Data Index: 5546001 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.5795. Min Act: -0.1700
Data Index: 6482 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.5482. Min Act: -0.1700
Data Index: 3781566 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.5482. Min Act: -0.1700
Data Index: 6578076 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.5482. Min Act: -0.1700
Data Index: 4352424 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.5482. Min Act: -0.1700
Data Index: 8467741 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.4857. Min Act: -0.1700
Data Index: 2855435 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5170. Min Range: -7.5170
Max Act: 6.4857. Min Act: -0.1700
Data Index: 4968532 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19