Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.2053. Min Act: -0.1700
Data Index: 3450422 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.1741. Min Act: -0.1700
Data Index: 1898467 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.1116. Min Act: -0.1700
Data Index: 6694188 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.0803. Min Act: -0.1700
Data Index: 6796170 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.0803. Min Act: -0.1700
Data Index: 4421241 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.0491. Min Act: -0.1700
Data Index: 7213183 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9241. Min Act: -0.1700
Data Index: 496861 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9241. Min Act: -0.1700
Data Index: 6995588 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8928. Min Act: -0.1700
Data Index: 3882176 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8928. Min Act: -0.1700
Data Index: 7732355 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8616. Min Act: -0.1700
Data Index: 5817603 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8616. Min Act: -0.1700
Data Index: 846019 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7678. Min Act: -0.1700
Data Index: 1462685 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7366. Min Act: -0.1700
Data Index: 7115887 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7366. Min Act: -0.1700
Data Index: 7462269 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7366. Min Act: -0.1700
Data Index: 7050246 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7053. Min Act: -0.1700
Data Index: 6973773 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7053. Min Act: -0.1700
Data Index: 6898667 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.6741. Min Act: -0.1700
Data Index: 3475630 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4862827 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19