Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5950. Min Act: -0.1700
Data Index: 225588 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5950. Min Act: -0.1700
Data Index: 7106132 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5638. Min Act: -0.1700
Data Index: 32714 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 1091628 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 5477947 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 5292153 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 1692303 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 4340524 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5325. Min Act: -0.1700
Data Index: 4767880 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5013. Min Act: -0.1700
Data Index: 2400484 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5013. Min Act: -0.1700
Data Index: 326053 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.5013. Min Act: -0.1700
Data Index: 1923952 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4700. Min Act: -0.1699
Data Index: 698330 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4388. Min Act: -0.1700
Data Index: 4966173 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4388. Min Act: -0.1700
Data Index: 6157554 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4075. Min Act: -0.1700
Data Index: 5640323 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4388. Min Act: -0.1700
Data Index: 2693430 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4075. Min Act: -0.1700
Data Index: 565437 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4075. Min Act: -0.1700
Data Index: 1201864 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5950. Min Range: -4.5950
Max Act: 4.4075. Min Act: -0.1700
Data Index: 1801928 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19