Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3835. Min Range: -6.3835
Max Act: 6.3835. Min Act: -0.1700
Data Index: 3966298 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3835. Min Range: -6.3835
Max Act: 6.1648. Min Act: -0.1700
Data Index: 6387698 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.8210. Min Act: -0.1700
Data Index: 4868741 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.8523. Min Act: -0.1700
Data Index: 5545663 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.8523. Min Act: -0.1700
Data Index: 4638333 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.7898. Min Act: -0.1700
Data Index: 264779 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.7585. Min Act: -0.1700
Data Index: 1587688 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 7278613 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6960. Min Act: -0.1700
Data Index: 2534769 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6648. Min Act: -0.1700
Data Index: 7743600 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6648. Min Act: -0.1700
Data Index: 2461879 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6648. Min Act: -0.1700
Data Index: 5426584 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6335. Min Act: -0.1700
Data Index: 2744405 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6335. Min Act: -0.1700
Data Index: 5232936 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6335. Min Act: -0.1700
Data Index: 97046 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.6023. Min Act: -0.1700
Data Index: 5397446 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.5710. Min Act: -0.1700
Data Index: 6755222 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.5710. Min Act: -0.1700
Data Index: 3444768 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.5710. Min Act: -0.1700
Data Index: 5398738 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3835. Min Range: -6.3835
Max Act: 5.5710. Min Act: -0.1700
Data Index: 1725513 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19