Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.4555. Min Act: -0.1700
Data Index: 2831933 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.2516. Min Act: -0.1700
Data Index: 930901 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.2516. Min Act: -0.1700
Data Index: 537821 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.2202. Min Act: -0.1700
Data Index: 4437306 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.2202. Min Act: -0.1700
Data Index: 8102144 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.2044. Min Act: -0.1700
Data Index: 2588111 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1572. Min Act: -0.1700
Data Index: 5596338 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1730. Min Act: -0.1700
Data Index: 7453973 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1572. Min Act: -0.1700
Data Index: 382471 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1415. Min Act: -0.1700
Data Index: 859641 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1415. Min Act: -0.1700
Data Index: 8397883 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1415. Min Act: -0.1700
Data Index: 6494800 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1572. Min Act: -0.1700
Data Index: 2627018 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1415. Min Act: -0.1700
Data Index: 2843601 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1258. Min Act: -0.1700
Data Index: 3826216 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1258. Min Act: -0.1700
Data Index: 6644995 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.1100. Min Act: -0.1700
Data Index: 4999529 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.0942. Min Act: -0.1700
Data Index: 4710845 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.0942. Min Act: -0.1700
Data Index: 1551535 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4555. Min Range: -3.4555
Max Act: 3.0942. Min Act: -0.1700
Data Index: 8102135 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19