Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.7640. Min Act: -0.1700
Data Index: 4721474 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.7640. Min Act: -0.1700
Data Index: 4847693 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.7171. Min Act: -0.1700
Data Index: 7124505 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6858. Min Act: -0.1700
Data Index: 3585977 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6702. Min Act: -0.1700
Data Index: 4614807 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6702. Min Act: -0.1700
Data Index: 4323926 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6702. Min Act: -0.1700
Data Index: 3028429 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6389. Min Act: -0.1700
Data Index: 3851667 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6389. Min Act: -0.1700
Data Index: 5448630 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6232. Min Act: -0.1700
Data Index: 7934794 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6232. Min Act: -0.1700
Data Index: 7779146 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6232. Min Act: -0.1700
Data Index: 2786608 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6076. Min Act: -0.1700
Data Index: 6380822 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.6076. Min Act: -0.1700
Data Index: 1203535 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5919. Min Act: -0.1700
Data Index: 6007935 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5763. Min Act: -0.1700
Data Index: 1242241 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5763. Min Act: -0.1700
Data Index: 2259141 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5763. Min Act: -0.1700
Data Index: 4554032 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5763. Min Act: -0.1700
Data Index: 6356473 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7640. Min Range: -3.7640
Max Act: 3.5763. Min Act: -0.1700
Data Index: 2129885 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19