Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 947 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1662. Min Range: -6.1662
Max Act: 6.1350. Min Act: -0.1700
Data Index: 1525195 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1662. Min Range: -6.1662
Max Act: 6.1662. Min Act: -0.1700
Data Index: 4471000 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1662. Min Range: -6.1662
Max Act: 6.1037. Min Act: -0.1700
Data Index: 4765752 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1662. Min Range: -6.1662
Max Act: 6.0725. Min Act: -0.1700
Data Index: 8389627 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1662. Min Range: -6.1662
Max Act: 6.0100. Min Act: -0.1700
Data Index: 6623719 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.9787. Min Act: -0.1700
Data Index: 4608516 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.9475. Min Act: -0.1700
Data Index: 6505305 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.9475. Min Act: -0.1700
Data Index: 1610275 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.9162. Min Act: -0.1700
Data Index: 6743063 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.8537. Min Act: -0.1700
Data Index: 5412512 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.8537. Min Act: -0.1700
Data Index: 2878495 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.8225. Min Act: -0.1700
Data Index: 393232 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.8225. Min Act: -0.1700
Data Index: 8532315 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.8225. Min Act: -0.1700
Data Index: 7141437 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4042546 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4958968 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7912. Min Act: -0.1700
Data Index: 1341627 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7600. Min Act: -0.1700
Data Index: 2973172 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7287. Min Act: -0.1700
Data Index: 3777587 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1662. Min Range: -6.1662
Max Act: 5.7287. Min Act: -0.1700
Data Index: 5787006 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19