Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.9943. Min Act: -0.1700
Data Index: 4308996 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8353540 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.7443. Min Act: -0.1700
Data Index: 2489033 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.7443. Min Act: -0.1700
Data Index: 8228487 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.7131. Min Act: -0.1700
Data Index: 6227335 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.6506. Min Act: -0.1700
Data Index: 5407284 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5568. Min Act: -0.1700
Data Index: 2797347 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5568. Min Act: -0.1700
Data Index: 3552367 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.5256. Min Act: -0.1700
Data Index: 8581038 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4943. Min Act: -0.1700
Data Index: 348458 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4631. Min Act: -0.1700
Data Index: 3459998 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4631. Min Act: -0.1700
Data Index: 2390816 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.4318. Min Act: -0.1700
Data Index: 4985115 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3693. Min Act: -0.1700
Data Index: 3199115 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3693. Min Act: -0.1700
Data Index: 7376428 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3381. Min Act: -0.1700
Data Index: 6985748 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3381. Min Act: -0.1700
Data Index: 3902368 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3068. Min Act: -0.1700
Data Index: 7879815 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3068. Min Act: -0.1700
Data Index: 5153270 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9943. Min Range: -5.9943
Max Act: 5.3068. Min Act: -0.1700
Data Index: 4749361 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19