Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3203. Min Range: -9.3203
Max Act: 9.3203. Min Act: -0.1700
Data Index: 4833362 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3203. Min Range: -9.3203
Max Act: 9.1953. Min Act: -0.1700
Data Index: 3018827 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3203. Min Range: -9.3203
Max Act: 9.1328. Min Act: -0.1700
Data Index: 4111677 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3203. Min Range: -9.3203
Max Act: 9.1328. Min Act: -0.1700
Data Index: 8579097 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3203. Min Range: -9.3203
Max Act: 9.0078. Min Act: -0.1700
Data Index: 6466872 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.9453. Min Act: -0.1700
Data Index: 2633894 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.8828. Min Act: -0.1700
Data Index: 3169040 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.8828. Min Act: -0.1700
Data Index: 7396574 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.8203. Min Act: -0.1700
Data Index: 7054276 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.6328. Min Act: -0.1700
Data Index: 1148355 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5703. Min Act: -0.1700
Data Index: 1852618 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5703. Min Act: -0.1700
Data Index: 4002765 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5703. Min Act: -0.1700
Data Index: 1424277 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5703. Min Act: -0.1700
Data Index: 6939253 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5078. Min Act: -0.1700
Data Index: 1747800 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5078. Min Act: -0.1700
Data Index: 8335600 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.5078. Min Act: -0.1700
Data Index: 403539 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.4453. Min Act: -0.1700
Data Index: 7828498 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.4453. Min Act: -0.1700
Data Index: 7608496 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3203. Min Range: -9.3203
Max Act: 8.4453. Min Act: -0.1700
Data Index: 6573539 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19