Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 8761589 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6921. Min Act: -0.1700
Data Index: 1143163 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6608. Min Act: -0.1700
Data Index: 6022330 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6296. Min Act: -0.1700
Data Index: 2021559 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6296. Min Act: -0.1700
Data Index: 625858 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6296. Min Act: -0.1700
Data Index: 6034572 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.6296. Min Act: -0.1700
Data Index: 6451954 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5983. Min Act: -0.1700
Data Index: 5752812 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5671. Min Act: -0.1700
Data Index: 4398192 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5671. Min Act: -0.1700
Data Index: 1436181 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5671. Min Act: -0.1700
Data Index: 6233225 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5358. Min Act: -0.1700
Data Index: 4338445 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5046. Min Act: -0.1700
Data Index: 4273346 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.5046. Min Act: -0.1700
Data Index: 6844143 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4733. Min Act: -0.1700
Data Index: 3879961 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4733. Min Act: -0.1700
Data Index: 7925016 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4733. Min Act: -0.1700
Data Index: 5770973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4733. Min Act: -0.1700
Data Index: 4427657 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4421. Min Act: -0.1700
Data Index: 959524 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8483. Min Range: -5.8483
Max Act: 5.4733. Min Act: -0.1700
Data Index: 8225891 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19