Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0234. Min Range: -9.0234
Max Act: 9.0234. Min Act: -0.1700
Data Index: 7738885 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.8359. Min Act: -0.1700
Data Index: 1196616 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.6484. Min Act: -0.1700
Data Index: 3644686 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.6484. Min Act: -0.1700
Data Index: 4530803 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5859. Min Act: -0.1700
Data Index: 7780253 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5859. Min Act: -0.1700
Data Index: 4615331 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 3644688 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 1442742 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5859. Min Act: -0.1700
Data Index: 4005643 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 3456942 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 3066629 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 8284721 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.5234. Min Act: -0.1700
Data Index: 3495266 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.4609. Min Act: -0.1700
Data Index: 6365089 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.4609. Min Act: -0.1700
Data Index: 3326038 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.4609. Min Act: -0.1700
Data Index: 3704479 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.4609. Min Act: -0.1700
Data Index: 4116269 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.2734. Min Act: -0.1700
Data Index: 1101184 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.3359. Min Act: -0.1700
Data Index: 5557820 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0234. Min Range: -9.0234
Max Act: 8.3359. Min Act: -0.1700
Data Index: 6365099 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19