Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.9984. Min Act: -0.1700
Data Index: 5031570 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0296. Min Range: -6.0296
Max Act: 6.0296. Min Act: -0.1700
Data Index: 5627365 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.9984. Min Act: -0.1700
Data Index: 3255511 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.9671. Min Act: -0.1700
Data Index: 4106697 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4630924 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8734. Min Act: -0.1700
Data Index: 7815382 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8421. Min Act: -0.1700
Data Index: 5681113 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8421. Min Act: -0.1700
Data Index: 3997964 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8734. Min Act: -0.1700
Data Index: 7063984 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8421. Min Act: -0.1700
Data Index: 6109156 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8109. Min Act: -0.1700
Data Index: 172448 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8109. Min Act: -0.1700
Data Index: 3446904 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.8109. Min Act: -0.1700
Data Index: 4894014 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7796. Min Act: -0.1700
Data Index: 574461 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7484. Min Act: -0.1700
Data Index: 6492230 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7484. Min Act: -0.1700
Data Index: 4097253 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3824423 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7171. Min Act: -0.1700
Data Index: 6623356 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.7171. Min Act: -0.1700
Data Index: 4072201 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0296. Min Range: -6.0296
Max Act: 5.6859. Min Act: -0.1700
Data Index: 1917125 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19