Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.7042. Min Act: -0.1700
Data Index: 4630853 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6417. Min Act: -0.1700
Data Index: 8294896 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6729. Min Act: -0.1700
Data Index: 7125604 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6729. Min Act: -0.1700
Data Index: 6433689 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6729. Min Act: -0.1700
Data Index: 1440551 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6729. Min Act: -0.1700
Data Index: 90969 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.7042. Min Act: -0.1700
Data Index: 4598354 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6104. Min Act: -0.1700
Data Index: 358552 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6417. Min Act: -0.1700
Data Index: 4844407 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6417. Min Act: -0.1700
Data Index: 90970 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6104. Min Act: -0.1700
Data Index: 3511358 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.6104. Min Act: -0.1700
Data Index: 8213369 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5479. Min Act: -0.1700
Data Index: 5090371 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5792. Min Act: -0.1700
Data Index: 5172944 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5792. Min Act: -0.1700
Data Index: 7813046 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5167. Min Act: -0.1700
Data Index: 8608415 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5479. Min Act: -0.1700
Data Index: 1358700 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5167. Min Act: -0.1700
Data Index: 1178348 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5167. Min Act: -0.1700
Data Index: 228025 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7042. Min Range: -4.7042
Max Act: 4.5167. Min Act: -0.1700
Data Index: 2842070 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19