Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.4671. Min Act: -0.1700
Data Index: 1399310 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.2796. Min Act: -0.1700
Data Index: 426929 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.2171. Min Act: -0.1700
Data Index: 7633123 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.2171. Min Act: -0.1700
Data Index: 6764132 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.1546. Min Act: -0.1700
Data Index: 1313102 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.1858. Min Act: -0.1700
Data Index: 1448070 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.1858. Min Act: -0.1700
Data Index: 883553 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.1858. Min Act: -0.1700
Data Index: 441099 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.1546. Min Act: -0.1700
Data Index: 883555 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.0921. Min Act: -0.1700
Data Index: 7745812 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.0921. Min Act: -0.1700
Data Index: 3816716 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.0608. Min Act: -0.1700
Data Index: 482191 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.0608. Min Act: -0.1700
Data Index: 6911380 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4671. Min Range: -5.4671
Max Act: 5.0296. Min Act: -0.1700
Data Index: 5349134 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1411423 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9671. Min Act: -0.1700
Data Index: 5867726 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9671. Min Act: -0.1700
Data Index: 3263762 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 7155079 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 3363322 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4671. Min Range: -5.4671
Max Act: 4.9046. Min Act: -0.1700
Data Index: 5193445 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19