Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.9461. Min Act: -0.1700
Data Index: 5566822 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.8836. Min Act: -0.1700
Data Index: 239970 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.7585. Min Act: -0.1700
Data Index: 2608805 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6646. Min Act: -0.1700
Data Index: 1092077 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6490. Min Act: -0.1700
Data Index: 1695164 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6490. Min Act: -0.1700
Data Index: 4273817 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6333. Min Act: -0.1700
Data Index: 6153014 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6177. Min Act: -0.1700
Data Index: 4581240 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.6020. Min Act: -0.1700
Data Index: 4579185 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.5864. Min Act: -0.1700
Data Index: 1553003 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.5394. Min Act: -0.1700
Data Index: 1934526 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.5238. Min Act: -0.1700
Data Index: 735144 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4768. Min Act: -0.1700
Data Index: 4792375 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4768. Min Act: -0.1700
Data Index: 1921884 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4768. Min Act: -0.1700
Data Index: 12307 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4611. Min Act: -0.1700
Data Index: 1797828 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4454. Min Act: -0.1700
Data Index: 8756049 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4454. Min Act: -0.1700
Data Index: 359891 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4611. Min Act: -0.1700
Data Index: 4688762 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9461. Min Range: -3.9461
Max Act: 3.4611. Min Act: -0.1700
Data Index: 598061 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19