Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0316. Min Range: -5.0316
Max Act: 5.0316. Min Act: -0.1700
Data Index: 3182640 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.9691. Min Act: -0.1700
Data Index: 1733411 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.9066. Min Act: -0.1700
Data Index: 5245081 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.8753. Min Act: -0.1700
Data Index: 4451838 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7816. Min Act: -0.1700
Data Index: 1626246 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7816. Min Act: -0.1700
Data Index: 1302802 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7816. Min Act: -0.1700
Data Index: 5597390 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7816. Min Act: -0.1700
Data Index: 4921682 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7816. Min Act: -0.1700
Data Index: 2064013 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7503. Min Act: -0.1700
Data Index: 2212604 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7503. Min Act: -0.1700
Data Index: 8200195 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7503. Min Act: -0.1700
Data Index: 4749665 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3274880 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7191. Min Act: -0.1700
Data Index: 6829288 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7191. Min Act: -0.1700
Data Index: 682925 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.7191. Min Act: -0.1700
Data Index: 7066838 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.6878. Min Act: -0.1700
Data Index: 2021887 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.6566. Min Act: -0.1700
Data Index: 6385238 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.6566. Min Act: -0.1700
Data Index: 4453588 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0316. Min Range: -5.0316
Max Act: 4.6566. Min Act: -0.1700
Data Index: 4658385 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19