Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3772. Min Range: -6.3772
Max Act: 6.3772. Min Act: -0.1700
Data Index: 7095638 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3772. Min Range: -6.3772
Max Act: 6.2834. Min Act: -0.1700
Data Index: 3092625 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3772. Min Range: -6.3772
Max Act: 6.1272. Min Act: -0.1700
Data Index: 1063890 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3772. Min Range: -6.3772
Max Act: 6.1272. Min Act: -0.1700
Data Index: 2710015 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3772. Min Range: -6.3772
Max Act: 6.0022. Min Act: -0.1700
Data Index: 2797354 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.9397. Min Act: -0.1700
Data Index: 4086710 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.9709. Min Act: -0.1700
Data Index: 3526860 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.9709. Min Act: -0.1700
Data Index: 5418730 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.9397. Min Act: -0.1700
Data Index: 544030 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.9084. Min Act: -0.1700
Data Index: 1002281 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.8772. Min Act: -0.1700
Data Index: 1973401 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.8147. Min Act: -0.1700
Data Index: 8621642 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1178540 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7522. Min Act: -0.1700
Data Index: 4061782 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1009785 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1898789 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1121135 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7209. Min Act: -0.1700
Data Index: 4453985 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1981067 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3772. Min Range: -6.3772
Max Act: 5.7209. Min Act: -0.1700
Data Index: 6335567 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19