Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 1052556 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.4022. Min Act: -0.1700
Data Index: 6156579 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.1522. Min Act: -0.1700
Data Index: 1846965 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.1834. Min Act: -0.1700
Data Index: 2825846 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.1209. Min Act: -0.1700
Data Index: 2616901 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.1209. Min Act: -0.1700
Data Index: 7014748 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.0584. Min Act: -0.1700
Data Index: 348225 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6522. Min Range: -7.6522
Max Act: 7.0272. Min Act: -0.1700
Data Index: 1263750 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9959. Min Act: -0.1700
Data Index: 5422576 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9959. Min Act: -0.1700
Data Index: 936662 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9647. Min Act: -0.1700
Data Index: 3112018 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9334. Min Act: -0.1700
Data Index: 5378553 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9334. Min Act: -0.1700
Data Index: 6238006 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9334. Min Act: -0.1700
Data Index: 3992566 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9022. Min Act: -0.1700
Data Index: 6512449 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9022. Min Act: -0.1700
Data Index: 3323185 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.9022. Min Act: -0.1700
Data Index: 1312876 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.8709. Min Act: -0.1700
Data Index: 1941634 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.8397. Min Act: -0.1700
Data Index: 1244705 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6522. Min Range: -7.6522
Max Act: 6.8084. Min Act: -0.1700
Data Index: 6477026 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19