Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.6609. Min Act: -0.1700
Data Index: 3433477 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.5671. Min Act: -0.1700
Data Index: 6777052 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.3796. Min Act: -0.1700
Data Index: 3291839 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2859. Min Act: -0.1700
Data Index: 6519112 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2546. Min Act: -0.1700
Data Index: 8561335 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.2234. Min Act: -0.1700
Data Index: 7403545 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 4970261 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 1698288 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 733438 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 5152249 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1921. Min Act: -0.1700
Data Index: 7161678 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 5494671 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 7457806 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 4345867 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 644093 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 7909726 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1296. Min Act: -0.1700
Data Index: 6402470 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 1816618 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1609. Min Act: -0.1700
Data Index: 7260800 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6609. Min Range: -6.6609
Max Act: 6.1296. Min Act: -0.1700
Data Index: 5088554 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19