Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 334 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.3418. Min Act: -0.1700
Data Index: 5588279 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1230. Min Act: -0.1700
Data Index: 2582764 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.0917. Min Act: -0.1700
Data Index: 470288 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.0605. Min Act: -0.1700
Data Index: 105725 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.0292. Min Act: -0.1700
Data Index: 715355 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9979. Min Act: -0.1700
Data Index: 4879416 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9979. Min Act: -0.1700
Data Index: 1138044 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.0292. Min Act: -0.1700
Data Index: 1971016 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.0292. Min Act: -0.1700
Data Index: 3260367 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9354. Min Act: -0.1700
Data Index: 6132684 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9667. Min Act: -0.1700
Data Index: 5446226 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9667. Min Act: -0.1700
Data Index: 5327254 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9667. Min Act: -0.1700
Data Index: 8796229 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8652617 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9354. Min Act: -0.1700
Data Index: 6933301 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9354. Min Act: -0.1700
Data Index: 2091471 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9354. Min Act: -0.1700
Data Index: 6306033 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9667. Min Act: -0.1700
Data Index: 1994496 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9042. Min Act: -0.1700
Data Index: 2464076 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3418. Min Range: -4.3418
Max Act: 3.9042. Min Act: -0.1700
Data Index: 2573562 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19