Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2658. Min Range: -5.2658
Max Act: 5.2658. Min Act: -0.1700
Data Index: 6823822 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2658. Min Range: -5.2658
Max Act: 5.2033. Min Act: -0.1700
Data Index: 7616253 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.9221. Min Act: -0.1700
Data Index: 6649721 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.9221. Min Act: -0.1700
Data Index: 6175826 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.8283. Min Act: -0.1700
Data Index: 6006796 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7971. Min Act: -0.1700
Data Index: 6649722 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7658. Min Act: -0.1700
Data Index: 2538907 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7658. Min Act: -0.1700
Data Index: 5725579 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7658. Min Act: -0.1700
Data Index: 8407581 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7658. Min Act: -0.1700
Data Index: 5365442 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7658. Min Act: -0.1700
Data Index: 6112334 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7346. Min Act: -0.1700
Data Index: 565780 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7346. Min Act: -0.1700
Data Index: 7435552 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.7033. Min Act: -0.1700
Data Index: 1879134 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.6721. Min Act: -0.1700
Data Index: 8411785 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.6408. Min Act: -0.1700
Data Index: 2013681 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.6408. Min Act: -0.1700
Data Index: 4855124 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.6408. Min Act: -0.1700
Data Index: 6667031 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.6096. Min Act: -0.1700
Data Index: 809363 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2658. Min Range: -5.2658
Max Act: 4.5783. Min Act: -0.1700
Data Index: 338584 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19