Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0016. Min Range: -7.0016
Max Act: 7.0016. Min Act: -0.1700
Data Index: 3275907 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.9703. Min Act: -0.1700
Data Index: 2403723 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.9391. Min Act: -0.1700
Data Index: 3320019 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.9391. Min Act: -0.1700
Data Index: 6688864 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8453. Min Act: -0.1700
Data Index: 3243771 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8766. Min Act: -0.1700
Data Index: 2860913 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8453. Min Act: -0.1700
Data Index: 8793281 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7828. Min Act: -0.1700
Data Index: 5091351 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8141. Min Act: -0.1700
Data Index: 5767276 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8141. Min Act: -0.1700
Data Index: 284866 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.8141. Min Act: -0.1700
Data Index: 7470761 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7828. Min Act: -0.1700
Data Index: 6789097 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7516. Min Act: -0.1700
Data Index: 3397823 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7516. Min Act: -0.1700
Data Index: 3486161 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7516. Min Act: -0.1700
Data Index: 7842267 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7516. Min Act: -0.1700
Data Index: 141022 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7203. Min Act: -0.1700
Data Index: 5312776 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7641277 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.6891. Min Act: -0.1700
Data Index: 2449693 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0016. Min Range: -7.0016
Max Act: 6.7203. Min Act: -0.1700
Data Index: 683289 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19