Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5751. Min Act: -0.1700
Data Index: 2638653 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 5554256 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 1455903 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4188. Min Act: -0.1700
Data Index: 7765552 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.3876. Min Act: -0.1700
Data Index: 510018 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.3563. Min Act: -0.1700
Data Index: 8557338 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2938. Min Act: -0.1700
Data Index: 1818663 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2626. Min Act: -0.1700
Data Index: 3289453 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2626. Min Act: -0.1700
Data Index: 3988418 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2626. Min Act: -0.1700
Data Index: 1539887 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2626. Min Act: -0.1700
Data Index: 2892169 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2313. Min Act: -0.1700
Data Index: 1736096 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2313. Min Act: -0.1700
Data Index: 8444233 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2313. Min Act: -0.1700
Data Index: 8144629 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.1688. Min Act: -0.1700
Data Index: 8453478 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.1376. Min Act: -0.1700
Data Index: 8667726 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.2001. Min Act: -0.1700
Data Index: 3334310 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.1376. Min Act: -0.1700
Data Index: 559480 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.1063. Min Act: -0.1700
Data Index: 194865 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.0751. Min Act: -0.1700
Data Index: 1046778 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19