Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.9383. Min Act: -0.1700
Data Index: 733461 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.9383. Min Act: -0.1700
Data Index: 3332180 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.9383. Min Act: -0.1700
Data Index: 4671551 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.9071. Min Act: -0.1700
Data Index: 7728224 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.8758. Min Act: -0.1700
Data Index: 3109014 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.8289. Min Act: -0.1700
Data Index: 4253151 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7820. Min Act: -0.1700
Data Index: 4203387 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.8133. Min Act: -0.1700
Data Index: 5052242 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7820. Min Act: -0.1700
Data Index: 2581854 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7663. Min Act: -0.1700
Data Index: 6502212 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7507. Min Act: -0.1700
Data Index: 7572609 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7663. Min Act: -0.1700
Data Index: 4157435 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7663. Min Act: -0.1700
Data Index: 2581853 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7663. Min Act: -0.1700
Data Index: 6396316 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7351. Min Act: -0.1700
Data Index: 3273403 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7351. Min Act: -0.1700
Data Index: 1481647 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7194. Min Act: -0.1700
Data Index: 4420347 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7194. Min Act: -0.1700
Data Index: 7043122 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7194. Min Act: -0.1700
Data Index: 8211792 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9383. Min Range: -3.9383
Max Act: 3.7194. Min Act: -0.1700
Data Index: 3090736 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19