Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0629. Min Range: -5.0629
Max Act: 5.0629. Min Act: -0.1700
Data Index: 3029809 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0629. Min Range: -5.0629
Max Act: 5.0317. Min Act: -0.1700
Data Index: 2528519 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0629. Min Range: -5.0629
Max Act: 5.0004. Min Act: -0.1700
Data Index: 8674627 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9692. Min Act: -0.1700
Data Index: 458730 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9692. Min Act: -0.1700
Data Index: 6881027 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9692. Min Act: -0.1700
Data Index: 3224805 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9379. Min Act: -0.1700
Data Index: 4119688 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9379. Min Act: -0.1700
Data Index: 793486 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.9067. Min Act: -0.1700
Data Index: 4829955 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4436375 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4436374 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.8442. Min Act: -0.1700
Data Index: 1747715 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7817. Min Act: -0.1700
Data Index: 8344005 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7817. Min Act: -0.1700
Data Index: 1396718 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.8129. Min Act: -0.1700
Data Index: 1133509 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4954034 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7817. Min Act: -0.1700
Data Index: 1580703 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4955744 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7504. Min Act: -0.1700
Data Index: 3317968 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0629. Min Range: -5.0629
Max Act: 4.7504. Min Act: -0.1700
Data Index: 6191429 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19