Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3093. Min Range: -7.3093
Max Act: 7.3093. Min Act: -0.1700
Data Index: 1477349 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3093. Min Range: -7.3093
Max Act: 7.2468. Min Act: -0.1700
Data Index: 269666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3093. Min Range: -7.3093
Max Act: 7.1531. Min Act: -0.1700
Data Index: 7382197 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3093. Min Range: -7.3093
Max Act: 7.0593. Min Act: -0.1700
Data Index: 7148441 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.9656. Min Act: -0.1700
Data Index: 7224242 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.9656. Min Act: -0.1700
Data Index: 4930019 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.8718. Min Act: -0.1700
Data Index: 4824559 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.8406. Min Act: -0.1700
Data Index: 7312479 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.8093. Min Act: -0.1700
Data Index: 3093443 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.7781. Min Act: -0.1700
Data Index: 4850719 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.7468. Min Act: -0.1700
Data Index: 1832041 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.7156. Min Act: -0.1700
Data Index: 4220344 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 1975472 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 8437049 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 5126441 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 5313435 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 4192054 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6843. Min Act: -0.1700
Data Index: 6446664 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6531. Min Act: -0.1700
Data Index: 2197645 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3093. Min Range: -7.3093
Max Act: 6.6218. Min Act: -0.1700
Data Index: 4907414 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19