Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.4003. Min Act: -0.1700
Data Index: 3044014 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.3375. Min Act: -0.1700
Data Index: 5373884 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.3062. Min Act: -0.1700
Data Index: 1610099 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.3062. Min Act: -0.1700
Data Index: 3557438 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.3062. Min Act: -0.1700
Data Index: 4396469 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2590. Min Act: -0.1700
Data Index: 3565272 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2590. Min Act: -0.1700
Data Index: 5276141 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2433. Min Act: -0.1700
Data Index: 2400674 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 6424375 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 6103096 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 2301132 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 1453330 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 1169648 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2276. Min Act: -0.1700
Data Index: 5245903 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.2119. Min Act: -0.1700
Data Index: 2640934 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.1962. Min Act: -0.1700
Data Index: 5580023 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.1962. Min Act: -0.1700
Data Index: 5418065 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.1962. Min Act: -0.1700
Data Index: 2211461 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.1804. Min Act: -0.1700
Data Index: 2076896 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4003. Min Range: -3.4003
Max Act: 3.1804. Min Act: -0.1700
Data Index: 1480035 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19