Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1198 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.8232. Min Act: -0.0001

Data Index: 380809 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7919. Min Act: -0.0001

Data Index: 562704 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7074. Min Act: -0.0001

Data Index: 788969 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6517. Min Act: -0.0001

Data Index: 683198 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6648. Min Act: -0.0001

Data Index: 926162 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7242. Min Act: -0.0001

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1072687 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5748. Min Act: -0.0001

Data Index: 870387 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6921. Min Act: -0.0001

Data Index: 629803 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6814. Min Act: -0.0002

Data Index: 55102 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6704. Min Act: -0.0001

Data Index: 616674 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6520. Min Act: -0.0001

Data Index: 182368 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6915. Min Act: -0.0001

Data Index: 793611 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6441. Min Act: -0.0001

Data Index: 358183 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6200. Min Act: -0.0001

Data Index: 106710 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6320. Min Act: -0.0001

Data Index: 105946 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6555. Min Act: -0.0001

Data Index: 601521 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6395. Min Act: -0.0001

Data Index: 174696 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6703. Min Act: -0.0002

Data Index: 958680 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1622565 (Python Code)

Max Activating Token Index: 665