Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.3538. Min Act: -0.1700
Data Index: 4273456 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.2288. Min Act: -0.1700
Data Index: 5853302 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.1351. Min Act: -0.1700
Data Index: 1250659 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.1663. Min Act: -0.1700
Data Index: 6253563 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.1038. Min Act: -0.1700
Data Index: 6986240 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.1038. Min Act: -0.1700
Data Index: 2578741 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0726. Min Act: -0.1700
Data Index: 3268301 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0726. Min Act: -0.1700
Data Index: 541102 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0101. Min Act: -0.1700
Data Index: 2339460 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0413. Min Act: -0.1700
Data Index: 7739882 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0101. Min Act: -0.1700
Data Index: 738158 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0101. Min Act: -0.1700
Data Index: 661530 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3538. Min Range: -6.3538
Max Act: 6.0101. Min Act: -0.1700
Data Index: 6764522 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9476. Min Act: -0.1700
Data Index: 2342705 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9788. Min Act: -0.1700
Data Index: 8667403 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9476. Min Act: -0.1700
Data Index: 889959 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9476. Min Act: -0.1700
Data Index: 2004055 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9476. Min Act: -0.1700
Data Index: 4294489 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9163. Min Act: -0.1700
Data Index: 1294755 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3538. Min Range: -6.3538
Max Act: 5.9476. Min Act: -0.1700
Data Index: 948664 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19