Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5594 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.6228. Min Act: -0.1700
Data Index: 211828 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.4666. Min Act: -0.1700
Data Index: 5226391 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.4041. Min Act: -0.1700
Data Index: 3530081 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.1853. Min Act: -0.1700
Data Index: 8227197 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.0603. Min Act: -0.1700
Data Index: 7976658 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.0603. Min Act: -0.1700
Data Index: 4349583 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.0291. Min Act: -0.1700
Data Index: 3419372 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6228. Min Range: -7.6228
Max Act: 7.0291. Min Act: -0.1700
Data Index: 3845219 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.9978. Min Act: -0.1700
Data Index: 1839247 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.9041. Min Act: -0.1700
Data Index: 2843401 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5811513 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.9041. Min Act: -0.1700
Data Index: 2467608 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8728. Min Act: -0.1700
Data Index: 1644034 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8416. Min Act: -0.1700
Data Index: 6718559 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8416. Min Act: -0.1700
Data Index: 2286182 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8103. Min Act: -0.1700
Data Index: 5706311 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8103. Min Act: -0.1700
Data Index: 1377231 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8103. Min Act: -0.1700
Data Index: 1054349 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.8103. Min Act: -0.1700
Data Index: 2015557 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6228. Min Range: -7.6228
Max Act: 6.7478. Min Act: -0.1700
Data Index: 1751394 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19