Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3663. Min Range: -5.3663
Max Act: 5.3663. Min Act: -0.1700
Data Index: 6923452 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.9913. Min Act: -0.1700
Data Index: 333307 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.9600. Min Act: -0.1700
Data Index: 5554445 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8975. Min Act: -0.1700
Data Index: 197505 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8663. Min Act: -0.1700
Data Index: 160157 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8350. Min Act: -0.1700
Data Index: 3782518 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8350. Min Act: -0.1700
Data Index: 1932886 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 6666600 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 8153669 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5207195 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 1013595 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 3271022 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 1915617 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 8701179 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 4558941 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 381639 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1601328 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1507086 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 6530878 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3663. Min Range: -5.3663
Max Act: 4.6788. Min Act: -0.1700
Data Index: 425536 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19