Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0678. Min Range: -5.0678
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6394531 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.8491. Min Act: -0.1700
Data Index: 370787 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.7866. Min Act: -0.1700
Data Index: 4809889 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.7553. Min Act: -0.1700
Data Index: 3412939 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.7553. Min Act: -0.1700
Data Index: 752265 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6817369 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.7241. Min Act: -0.1700
Data Index: 3902434 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6928. Min Act: -0.1700
Data Index: 410160 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6928. Min Act: -0.1700
Data Index: 7389126 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6616. Min Act: -0.1700
Data Index: 8303672 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7987236 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6303. Min Act: -0.1700
Data Index: 4135908 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6303. Min Act: -0.1700
Data Index: 4017535 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6616. Min Act: -0.1700
Data Index: 6656967 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7891713 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.5991. Min Act: -0.1700
Data Index: 4762031 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.5991. Min Act: -0.1700
Data Index: 3577934 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.5678. Min Act: -0.1700
Data Index: 319214 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.5678. Min Act: -0.1700
Data Index: 5362230 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0678. Min Range: -5.0678
Max Act: 4.5366. Min Act: -0.1700
Data Index: 4946893 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19