Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 80 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.9177. Min Act: -0.1700
Data Index: 45214 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.9177. Min Act: -0.1700
Data Index: 789694 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.9490. Min Act: -0.1700
Data Index: 981530 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.9177. Min Act: -0.1700
Data Index: 607705 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.9177. Min Act: -0.1700
Data Index: 183522 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 459954 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 559938 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7615. Min Act: -0.1700
Data Index: 192979 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 66334 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 518431 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 635840 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.8240. Min Act: -0.1700
Data Index: 456214 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1350477 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7927. Min Act: -0.1700
Data Index: 1278545 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.6365. Min Act: -0.1700
Data Index: 40259 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.6990. Min Act: -0.1700
Data Index: 1134137 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.6990. Min Act: -0.1700
Data Index: 652732 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7302. Min Act: -0.1700
Data Index: 891488 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7615. Min Act: -0.1700
Data Index: 634689 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9490. Min Range: -4.9490
Max Act: 4.7302. Min Act: -0.1700
Data Index: 42199 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19