Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1801. Min Range: -8.1801
Max Act: 8.1801. Min Act: -0.1700
Data Index: 4334802 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.8676. Min Act: -0.1700
Data Index: 731716 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.8676. Min Act: -0.1700
Data Index: 1133062 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.7426. Min Act: -0.1700
Data Index: 3810598 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.7426. Min Act: -0.1700
Data Index: 2696547 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.6801. Min Act: -0.1700
Data Index: 5612417 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.6176. Min Act: -0.1700
Data Index: 6800678 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.6176. Min Act: -0.1700
Data Index: 6265632 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.6176. Min Act: -0.1700
Data Index: 732193 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5551. Min Act: -0.1700
Data Index: 7247221 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5551. Min Act: -0.1700
Data Index: 7094217 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.6176. Min Act: -0.1700
Data Index: 6685406 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5551. Min Act: -0.1700
Data Index: 3885351 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5551. Min Act: -0.1700
Data Index: 2223923 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5551. Min Act: -0.1700
Data Index: 1349327 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5238. Min Act: -0.1700
Data Index: 637107 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5238. Min Act: -0.1700
Data Index: 1884143 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5238. Min Act: -0.1700
Data Index: 1444844 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5238. Min Act: -0.1700
Data Index: 6764346 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1801. Min Range: -8.1801
Max Act: 7.5238. Min Act: -0.1700
Data Index: 702033 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19