Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4797 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.8354. Min Act: -0.1700
Data Index: 832534 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.6479. Min Act: -0.1700
Data Index: 8397549 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.6479. Min Act: -0.1700
Data Index: 959954 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.5854. Min Act: -0.1700
Data Index: 4202411 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.5854. Min Act: -0.1700
Data Index: 8485293 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.5854. Min Act: -0.1700
Data Index: 5666765 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.5229. Min Act: -0.1700
Data Index: 2803834 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.5229. Min Act: -0.1700
Data Index: 6804834 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.4604. Min Act: -0.1700
Data Index: 8544379 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.4604. Min Act: -0.1700
Data Index: 3887416 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.4604. Min Act: -0.1700
Data Index: 1807831 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3979. Min Act: -0.1700
Data Index: 1606186 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3979. Min Act: -0.1700
Data Index: 6099936 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3354. Min Act: -0.1700
Data Index: 4203955 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3979. Min Act: -0.1700
Data Index: 7274940 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3979. Min Act: -0.1700
Data Index: 7302877 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.2729. Min Act: -0.1700
Data Index: 2966922 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3354. Min Act: -0.1700
Data Index: 1266525 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3354. Min Act: -0.1700
Data Index: 1446363 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8354. Min Range: -8.8354
Max Act: 8.3354. Min Act: -0.1700
Data Index: 1347179 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19