Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4516 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.8385. Min Act: -0.1700
Data Index: 3934162 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.7465. Min Act: -0.1696
Data Index: 5986547 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.7465. Min Act: -0.1682
Data Index: 7665188 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.7136. Min Act: -0.1700
Data Index: 3739092 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6891. Min Act: -0.1700
Data Index: 6170448 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6567. Min Act: -0.1681
Data Index: 4823295 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6567. Min Act: -0.1700
Data Index: 3959397 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6327. Min Act: -0.1700
Data Index: 2200020 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6327. Min Act: -0.1695
Data Index: 813870 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6247. Min Act: -0.1619
Data Index: 2674420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6247. Min Act: -0.1694
Data Index: 275391 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6168. Min Act: -0.1695
Data Index: 3058364 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6089. Min Act: -0.1615
Data Index: 5561091 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6168. Min Act: -0.1699
Data Index: 660677 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.6010. Min Act: -0.1689
Data Index: 8783368 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.5932. Min Act: -0.1700
Data Index: 5526408 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.5932. Min Act: -0.1699
Data Index: 5495900 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.5932. Min Act: -0.1688
Data Index: 5413421 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.5932. Min Act: -0.1699
Data Index: 8531644 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8385. Min Range: -0.8385
Max Act: 0.5853. Min Act: -0.1700
Data Index: 5612568 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19