Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3231. Min Range: -8.3231
Max Act: 8.3231. Min Act: -0.1700
Data Index: 6913781 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3231. Min Range: -8.3231
Max Act: 8.1981. Min Act: -0.1700
Data Index: 7537041 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.9168. Min Act: -0.1700
Data Index: 8362285 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.9168. Min Act: -0.1700
Data Index: 5687272 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.8856. Min Act: -0.1700
Data Index: 4795538 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.8543. Min Act: -0.1700
Data Index: 3287143 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.8543. Min Act: -0.1700
Data Index: 6053743 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.8231. Min Act: -0.1700
Data Index: 4102434 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.7606. Min Act: -0.1700
Data Index: 7368016 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.7293. Min Act: -0.1700
Data Index: 6704160 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.7293. Min Act: -0.1700
Data Index: 3542555 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.7293. Min Act: -0.1700
Data Index: 244512 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6981. Min Act: -0.1700
Data Index: 1398336 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6356. Min Act: -0.1700
Data Index: 6963362 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6668. Min Act: -0.1700
Data Index: 6595155 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6356. Min Act: -0.1700
Data Index: 3051246 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6668. Min Act: -0.1700
Data Index: 5677268 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6043. Min Act: -0.1700
Data Index: 7102821 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.6043. Min Act: -0.1700
Data Index: 3883690 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3231. Min Range: -8.3231
Max Act: 7.5731. Min Act: -0.1700
Data Index: 5149638 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19