Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1405. Min Range: -7.1405
Max Act: 7.1405. Min Act: -0.1700
Data Index: 2223805 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1405. Min Range: -7.1405
Max Act: 7.0468. Min Act: -0.1700
Data Index: 2877638 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.9843. Min Act: -0.1700
Data Index: 8151571 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.9843. Min Act: -0.1700
Data Index: 4667676 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.9218. Min Act: -0.1700
Data Index: 5590918 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.9530. Min Act: -0.1700
Data Index: 302770 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.8905. Min Act: -0.1700
Data Index: 2838233 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.8593. Min Act: -0.1700
Data Index: 6826967 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.8280. Min Act: -0.1700
Data Index: 3350685 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7655. Min Act: -0.1700
Data Index: 8783756 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 4703535 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7343. Min Act: -0.1700
Data Index: 8287488 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 7815970 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 3148882 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 455497 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 7660919 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.7030. Min Act: -0.1700
Data Index: 8322083 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.6405. Min Act: -0.1700
Data Index: 1622354 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.6718. Min Act: -0.1700
Data Index: 6480183 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1405. Min Range: -7.1405
Max Act: 6.6718. Min Act: -0.1700
Data Index: 5808625 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19