Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1165 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.9671. Min Act: -0.1700
Data Index: 4602335 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8420. Min Act: -0.1700
Data Index: 8072589 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8420. Min Act: -0.1700
Data Index: 8090695 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8107. Min Act: -0.1700
Data Index: 4408002 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8107. Min Act: -0.1700
Data Index: 4638021 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1726584 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7795. Min Act: -0.1700
Data Index: 3010487 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7795. Min Act: -0.1700
Data Index: 904831 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7795. Min Act: -0.1700
Data Index: 965851 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1315603 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 648184 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 4352908 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 5656818 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 5482511 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 7734477 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 8800215 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7795. Min Act: -0.1698
Data Index: 4928469 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 6679749 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7795. Min Act: -0.1700
Data Index: 6482767 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9671. Min Range: -3.9671
Max Act: 3.7482. Min Act: -0.1700
Data Index: 2991202 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19