Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5336. Min Range: -8.5336
Max Act: 8.5336. Min Act: -0.1700
Data Index: 885125 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5336. Min Range: -8.5336
Max Act: 8.0336. Min Act: -0.1700
Data Index: 1767278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.9711. Min Act: -0.1700
Data Index: 4007050 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.9711. Min Act: -0.1700
Data Index: 1958473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.8773. Min Act: -0.1700
Data Index: 2324284 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.8461. Min Act: -0.1700
Data Index: 3411551 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.8461. Min Act: -0.1700
Data Index: 622199 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.8461. Min Act: -0.1700
Data Index: 4041678 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.8461. Min Act: -0.1700
Data Index: 6145062 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.7836. Min Act: -0.1700
Data Index: 152364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.7211. Min Act: -0.1700
Data Index: 6540657 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.7523. Min Act: -0.1700
Data Index: 3207191 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6898. Min Act: -0.1700
Data Index: 8668008 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6898. Min Act: -0.1700
Data Index: 5348798 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6273. Min Act: -0.1700
Data Index: 6579326 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6586. Min Act: -0.1700
Data Index: 1049744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6273. Min Act: -0.1700
Data Index: 8033939 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.6273. Min Act: -0.1700
Data Index: 8697687 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.5648. Min Act: -0.1700
Data Index: 1540790 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5336. Min Range: -8.5336
Max Act: 7.5961. Min Act: -0.1700
Data Index: 7122923 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19