Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.8604. Min Act: -0.1700
Data Index: 7998447 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.7354. Min Act: -0.1700
Data Index: 1516532 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.6729. Min Act: -0.1700
Data Index: 265533 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.6729. Min Act: -0.1700
Data Index: 1928797 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.6729. Min Act: -0.1700
Data Index: 1288948 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.7354. Min Act: -0.1700
Data Index: 525654 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.5479. Min Act: -0.1700
Data Index: 7039594 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.5479. Min Act: -0.1700
Data Index: 7727098 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.4854. Min Act: -0.1700
Data Index: 3103198 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.4854. Min Act: -0.1700
Data Index: 1075717 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.4854. Min Act: -0.1700
Data Index: 6520204 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.4229. Min Act: -0.1700
Data Index: 5602446 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.4229. Min Act: -0.1700
Data Index: 7652313 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.3604. Min Act: -0.1700
Data Index: 5519853 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.3604. Min Act: -0.1700
Data Index: 8151801 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.3604. Min Act: -0.1700
Data Index: 8113703 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.2979. Min Act: -0.1700
Data Index: 5177276 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.2979. Min Act: -0.1700
Data Index: 4489784 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.2979. Min Act: -0.1700
Data Index: 6226061 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8604. Min Range: -8.8604
Max Act: 8.2979. Min Act: -0.1700
Data Index: 8063836 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19