Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6135 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.8337. Min Act: -0.1697
Data Index: 6507721 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.7087. Min Act: -0.1700
Data Index: 4792302 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5837. Min Act: -0.1700
Data Index: 4679567 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5212. Min Act: -0.1698
Data Index: 5187644 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5212. Min Act: -0.1700
Data Index: 4518505 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.5525. Min Act: -0.1698
Data Index: 8778370 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4900. Min Act: -0.1700
Data Index: 1854637 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3178856 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4900. Min Act: -0.1700
Data Index: 1499343 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 2182725 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 7874145 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 7832702 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 7290562 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 3616840 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4587. Min Act: -0.1700
Data Index: 6729316 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5356238 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.3962. Min Act: -0.1700
Data Index: 3796231 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4275. Min Act: -0.1700
Data Index: 7971907 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5955469 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8337. Min Range: -5.8337
Max Act: 5.3962. Min Act: -0.1700
Data Index: 2149869 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19