Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.4647. Min Act: -0.1700
Data Index: 7914289 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.4334. Min Act: -0.1700
Data Index: 4893542 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.3397. Min Act: -0.1700
Data Index: 7836181 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.3084. Min Act: -0.1700
Data Index: 1818366 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.3084. Min Act: -0.1700
Data Index: 3471781 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2772. Min Act: -0.1700
Data Index: 5334201 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2772. Min Act: -0.1700
Data Index: 5756126 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2772. Min Act: -0.1700
Data Index: 4151817 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2772. Min Act: -0.1700
Data Index: 8737979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2459. Min Act: -0.1700
Data Index: 6764794 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2459. Min Act: -0.1700
Data Index: 205593 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2147. Min Act: -0.1700
Data Index: 4862002 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.2147. Min Act: -0.1700
Data Index: 1386095 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1834. Min Act: -0.1700
Data Index: 621511 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1522. Min Act: -0.1700
Data Index: 69974 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1522. Min Act: -0.1700
Data Index: 1555965 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1522. Min Act: -0.1700
Data Index: 3217978 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1522. Min Act: -0.1700
Data Index: 5756127 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.1209. Min Act: -0.1700
Data Index: 1533306 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4647. Min Range: -5.4647
Max Act: 5.0897. Min Act: -0.1700
Data Index: 2138466 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19