Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1957. Min Act: -0.1700
Data Index: 4431482 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1645. Min Act: -0.1700
Data Index: 7882135 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1645. Min Act: -0.1700
Data Index: 7882128 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1332. Min Act: -0.1700
Data Index: 3932803 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1332. Min Act: -0.1700
Data Index: 4632143 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1332. Min Act: -0.1700
Data Index: 1958826 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.1019. Min Act: -0.1700
Data Index: 823879 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0707. Min Act: -0.1700
Data Index: 1404343 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0707. Min Act: -0.1700
Data Index: 4984492 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0394. Min Act: -0.1700
Data Index: 4410989 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0394. Min Act: -0.1700
Data Index: 2297703 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0394. Min Act: -0.1700
Data Index: 6206509 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1957. Min Range: -4.1957
Max Act: 4.0082. Min Act: -0.1700
Data Index: 3439355 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9769. Min Act: -0.1700
Data Index: 1831049 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9456. Min Act: -0.1700
Data Index: 2108054 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9769. Min Act: -0.1700
Data Index: 7247732 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9456. Min Act: -0.1700
Data Index: 1161797 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9769. Min Act: -0.1700
Data Index: 7640179 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9456. Min Act: -0.1700
Data Index: 6900940 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1957. Min Range: -4.1957
Max Act: 3.9456. Min Act: -0.1700
Data Index: 4739522 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19