Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2917. Min Range: -5.2917
Max Act: 5.2917. Min Act: -0.1700
Data Index: 8178028 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.9792. Min Act: -0.1700
Data Index: 8643669 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.9167. Min Act: -0.1700
Data Index: 8300246 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.8854. Min Act: -0.1700
Data Index: 5416888 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.8854. Min Act: -0.1700
Data Index: 8602842 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.8854. Min Act: -0.1700
Data Index: 1910107 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.8542. Min Act: -0.1700
Data Index: 6070417 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7917. Min Act: -0.1700
Data Index: 2734812 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 5883852 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7917. Min Act: -0.1700
Data Index: 8227127 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 357199 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 5179473 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 477191 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 7727248 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.6979. Min Act: -0.1700
Data Index: 2485429 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7292. Min Act: -0.1700
Data Index: 3340877 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.7604. Min Act: -0.1700
Data Index: 928862 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.6979. Min Act: -0.1700
Data Index: 2439478 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.6667. Min Act: -0.1700
Data Index: 4857923 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2917. Min Range: -5.2917
Max Act: 4.6667. Min Act: -0.1700
Data Index: 8492361 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19