Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1476 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.5571. Min Act: -0.1700
Data Index: 7449566 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.4946. Min Act: -0.1700
Data Index: 952805 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.4321. Min Act: -0.1700
Data Index: 5043010 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.1196. Min Act: -0.1700
Data Index: 6153691 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.1196. Min Act: -0.1700
Data Index: 2014237 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.1196. Min Act: -0.1700
Data Index: 5690874 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.0571. Min Act: -0.1700
Data Index: 6573375 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5571. Min Range: -9.5571
Max Act: 9.0571. Min Act: -0.1700
Data Index: 5408449 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.9946. Min Act: -0.1700
Data Index: 5908469 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.9946. Min Act: -0.1700
Data Index: 2301939 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.9321. Min Act: -0.1700
Data Index: 1583326 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.9321. Min Act: -0.1700
Data Index: 4857305 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8696. Min Act: -0.1700
Data Index: 1831852 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8696. Min Act: -0.1700
Data Index: 8000965 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8696. Min Act: -0.1700
Data Index: 4127790 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8071. Min Act: -0.1700
Data Index: 5867553 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8071. Min Act: -0.1700
Data Index: 5589685 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8071. Min Act: -0.1700
Data Index: 6020288 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.8071. Min Act: -0.1700
Data Index: 1656019 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5571. Min Range: -9.5571
Max Act: 8.7446. Min Act: -0.1700
Data Index: 5238746 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19