Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.9215. Min Act: -0.1700
Data Index: 3535081 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.7653. Min Act: -0.1700
Data Index: 2259931 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.3903. Min Act: -0.1700
Data Index: 1922816 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.2653. Min Act: -0.1700
Data Index: 778327 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.1715. Min Act: -0.1700
Data Index: 3532227 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.1090. Min Act: -0.1700
Data Index: 6665695 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.1715. Min Act: -0.1700
Data Index: 3615445 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.1090. Min Act: -0.1700
Data Index: 1037160 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.1090. Min Act: -0.1700
Data Index: 4513980 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.0153. Min Act: -0.1700
Data Index: 6771545 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9215. Min Range: -7.9215
Max Act: 7.0153. Min Act: -0.1700
Data Index: 875618 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8590. Min Act: -0.1700
Data Index: 6448931 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8590. Min Act: -0.1700
Data Index: 5470418 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8278. Min Act: -0.1700
Data Index: 2567149 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8590. Min Act: -0.1700
Data Index: 4568636 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8278. Min Act: -0.1700
Data Index: 89603 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8278. Min Act: -0.1700
Data Index: 4934107 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.8590. Min Act: -0.1700
Data Index: 1242803 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.7965. Min Act: -0.1700
Data Index: 3397663 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9215. Min Range: -7.9215
Max Act: 6.7965. Min Act: -0.1700
Data Index: 6137602 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19