Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1434 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.6641. Min Act: -0.1700
Data Index: 8438766 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.5078. Min Act: -0.1700
Data Index: 7200574 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.2578. Min Act: -0.1700
Data Index: 742672 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.1328. Min Act: -0.1700
Data Index: 2884107 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.1641. Min Act: -0.1700
Data Index: 413664 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6641. Min Range: -6.6641
Max Act: 6.0078. Min Act: -0.1700
Data Index: 6572725 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.9766. Min Act: -0.1700
Data Index: 4475007 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7891. Min Act: -0.1700
Data Index: 6185180 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7891. Min Act: -0.1700
Data Index: 6857925 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 4501267 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7891. Min Act: -0.1700
Data Index: 643786 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 1299642 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 1284110 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 2873220 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6328. Min Act: -0.1700
Data Index: 5298676 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6641. Min Act: -0.1700
Data Index: 2339452 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6641. Min Act: -0.1700
Data Index: 2258519 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6641. Min Act: -0.1700
Data Index: 6361028 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6328. Min Act: -0.1700
Data Index: 7160441 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6641. Min Range: -6.6641
Max Act: 5.6328. Min Act: -0.1700
Data Index: 6717214 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19