Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.4425. Min Act: -0.1700
Data Index: 7428568 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.3800. Min Act: -0.1700
Data Index: 3794621 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.3175. Min Act: -0.1700
Data Index: 2894621 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1925. Min Act: -0.1700
Data Index: 7494304 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.2550. Min Act: -0.1700
Data Index: 8183265 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.2550. Min Act: -0.1700
Data Index: 1815270 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.2550. Min Act: -0.1700
Data Index: 7428570 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.2550. Min Act: -0.1700
Data Index: 2627957 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.2550. Min Act: -0.1700
Data Index: 1198935 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1925. Min Act: -0.1700
Data Index: 7971962 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1925. Min Act: -0.1700
Data Index: 8608109 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1925. Min Act: -0.1700
Data Index: 2752782 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1925. Min Act: -0.1700
Data Index: 5628095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 3860900 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 2508555 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 7212025 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 5595025 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 6456263 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 2322480 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4425. Min Range: -7.4425
Max Act: 7.1613. Min Act: -0.1700
Data Index: 5498097 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19