Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2079. Min Range: -6.2079
Max Act: 6.2079. Min Act: -0.1700
Data Index: 2773670 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2079. Min Range: -6.2079
Max Act: 6.2079. Min Act: -0.1700
Data Index: 2177201 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2079. Min Range: -6.2079
Max Act: 6.1142. Min Act: -0.1700
Data Index: 2528480 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2079. Min Range: -6.2079
Max Act: 6.0517. Min Act: -0.1700
Data Index: 2036091 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8642. Min Act: -0.1700
Data Index: 2101025 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.9267. Min Act: -0.1700
Data Index: 5615961 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8954. Min Act: -0.1700
Data Index: 7742364 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8642. Min Act: -0.1700
Data Index: 2716693 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8642. Min Act: -0.1700
Data Index: 6305567 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8329. Min Act: -0.1700
Data Index: 5932508 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8329. Min Act: -0.1700
Data Index: 4874359 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8329. Min Act: -0.1700
Data Index: 6769228 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8329. Min Act: -0.1700
Data Index: 5649508 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8329. Min Act: -0.1700
Data Index: 2909164 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8017. Min Act: -0.1700
Data Index: 3284678 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.8017. Min Act: -0.1700
Data Index: 966759 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.7704. Min Act: -0.1700
Data Index: 6858713 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.7392. Min Act: -0.1700
Data Index: 6506208 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.7392. Min Act: -0.1700
Data Index: 1626495 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2079. Min Range: -6.2079
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5733345 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19