Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4394 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2544. Min Range: -8.2544
Max Act: 8.2544. Min Act: -0.1700
Data Index: 6690353 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.9419. Min Act: -0.1700
Data Index: 452307 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.8794. Min Act: -0.1700
Data Index: 5888203 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.8169. Min Act: -0.1700
Data Index: 8642791 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.8169. Min Act: -0.1700
Data Index: 4600602 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.8169. Min Act: -0.1700
Data Index: 4131914 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.7856. Min Act: -0.1700
Data Index: 8183174 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.7231. Min Act: -0.1700
Data Index: 5403170 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.7231. Min Act: -0.1700
Data Index: 6266471 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.6294. Min Act: -0.1700
Data Index: 6718175 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5669. Min Act: -0.1700
Data Index: 6313625 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5981. Min Act: -0.1700
Data Index: 2898570 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5669. Min Act: -0.1700
Data Index: 1211865 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5356. Min Act: -0.1700
Data Index: 3151850 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5356. Min Act: -0.1700
Data Index: 2123084 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5044. Min Act: -0.1700
Data Index: 1751293 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5356. Min Act: -0.1700
Data Index: 7387986 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.5044. Min Act: -0.1700
Data Index: 7365299 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.4731. Min Act: -0.1700
Data Index: 7966623 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2544. Min Range: -8.2544
Max Act: 7.4731. Min Act: -0.1700
Data Index: 1984133 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19