Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.1442. Min Act: -0.1700
Data Index: 3633412 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5437895 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.0817. Min Act: -0.1700
Data Index: 2803449 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9567. Min Act: -0.1700
Data Index: 6749330 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9255. Min Act: -0.1700
Data Index: 5942657 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 2646545 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 2017921 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 1482912 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 5717831 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7888449 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6043982 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 2270529 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1963861 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4947596 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.7380. Min Act: -0.1700
Data Index: 1423141 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.7067. Min Act: -0.1700
Data Index: 2298203 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.6755. Min Act: -0.1700
Data Index: 8801920 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.6442. Min Act: -0.1700
Data Index: 444743 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.6755. Min Act: -0.1700
Data Index: 8209107 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.6755. Min Act: -0.1700
Data Index: 4477833 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19