Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.8510. Min Act: -0.1700
Data Index: 5952037 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.4760. Min Act: -0.1700
Data Index: 6960581 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.4135. Min Act: -0.1700
Data Index: 1579779 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.4135. Min Act: -0.1700
Data Index: 4615804 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.3510. Min Act: -0.1700
Data Index: 7160210 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.3510. Min Act: -0.1700
Data Index: 5127153 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.3510. Min Act: -0.1700
Data Index: 7050867 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2885. Min Act: -0.1700
Data Index: 4481597 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2885. Min Act: -0.1700
Data Index: 5483640 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2885. Min Act: -0.1700
Data Index: 5646422 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2885. Min Act: -0.1700
Data Index: 5767002 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 6329097 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 2894327 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 3985333 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 4379116 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.2260. Min Act: -0.1700
Data Index: 8062249 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.1635. Min Act: -0.1700
Data Index: 4576137 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.1635. Min Act: -0.1700
Data Index: 2376756 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.1010. Min Act: -0.1700
Data Index: 6345323 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8510. Min Range: -9.8510
Max Act: 9.1635. Min Act: -0.1700
Data Index: 4229644 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19