Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 211 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3137. Min Range: -6.3137
Max Act: 6.3137. Min Act: -0.1700
Data Index: 3138808 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3137. Min Range: -6.3137
Max Act: 6.1262. Min Act: -0.1700
Data Index: 1308457 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3137. Min Range: -6.3137
Max Act: 6.0949. Min Act: -0.1700
Data Index: 5440002 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3137. Min Range: -6.3137
Max Act: 6.0949. Min Act: -0.1700
Data Index: 8018202 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.9699. Min Act: -0.1700
Data Index: 1064862 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.7824. Min Act: -0.1700
Data Index: 8727692 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.7824. Min Act: -0.1700
Data Index: 5303758 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.7199. Min Act: -0.1700
Data Index: 4445148 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.7199. Min Act: -0.1700
Data Index: 6860323 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.6887. Min Act: -0.1700
Data Index: 6446195 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.6262. Min Act: -0.1700
Data Index: 3340894 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5949. Min Act: -0.1700
Data Index: 1554156 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5949. Min Act: -0.1700
Data Index: 322645 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5637. Min Act: -0.1700
Data Index: 6923572 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5324. Min Act: -0.1700
Data Index: 4335610 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5012. Min Act: -0.1700
Data Index: 7556048 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5324. Min Act: -0.1700
Data Index: 2916661 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.4699. Min Act: -0.1700
Data Index: 4339789 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5012. Min Act: -0.1700
Data Index: 1610074 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3137. Min Range: -6.3137
Max Act: 5.5012. Min Act: -0.1700
Data Index: 5394572 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19