Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.8493. Min Act: -0.1700
Data Index: 5893585 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.8806. Min Act: -0.1700
Data Index: 5934585 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.8180. Min Act: -0.1700
Data Index: 4171394 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7711. Min Act: -0.1700
Data Index: 7439012 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7711. Min Act: -0.1700
Data Index: 7117869 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7555. Min Act: -0.1700
Data Index: 3247792 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7399. Min Act: -0.1700
Data Index: 5427545 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7086. Min Act: -0.1700
Data Index: 8039129 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.7242. Min Act: -0.1700
Data Index: 3247793 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6929. Min Act: -0.1700
Data Index: 8206605 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6460. Min Act: -0.1700
Data Index: 7439014 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6616. Min Act: -0.1700
Data Index: 3106022 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6773. Min Act: -0.1700
Data Index: 5192505 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6303. Min Act: -0.1700
Data Index: 6462461 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6303. Min Act: -0.1700
Data Index: 7471033 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6303. Min Act: -0.1700
Data Index: 5734031 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6147. Min Act: -0.1700
Data Index: 887790 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6147. Min Act: -0.1700
Data Index: 6116627 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.6147. Min Act: -0.1700
Data Index: 8289998 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8806. Min Range: -3.8806
Max Act: 3.5990. Min Act: -0.1700
Data Index: 3451163 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19