Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.5638. Min Act: -0.1700
Data Index: 4990281 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.5013. Min Act: -0.1700
Data Index: 5000620 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.5013. Min Act: -0.1700
Data Index: 3913734 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.4075. Min Act: -0.1700
Data Index: 4161790 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.3763. Min Act: -0.1700
Data Index: 6078315 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3928622 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.3138. Min Act: -0.1700
Data Index: 5007848 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2825. Min Act: -0.1700
Data Index: 4054817 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7650390 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.3450. Min Act: -0.1700
Data Index: 925521 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7984378 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2825. Min Act: -0.1700
Data Index: 8545285 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2513. Min Act: -0.1700
Data Index: 7725220 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2513. Min Act: -0.1700
Data Index: 4099028 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 3762435 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5119438 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 2363944 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 4420266 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 7422716 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5638. Min Range: -5.5638
Max Act: 5.2200. Min Act: -0.1700
Data Index: 3951485 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19