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

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

Neuron 2033 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1105538 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2894. Min Act: -0.0000

Data Index: 193078 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2777. Min Act: -0.0000

Data Index: 909739 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1331148 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2626. Min Act: -0.0000

Data Index: 645242 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1046320 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2557. Min Act: -0.0001

Data Index: 803473 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1302022 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2226. Min Act: -0.0000

Data Index: 397316 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1422979 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2294. Min Act: -0.0000

Data Index: 803521 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1225532 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2303. Min Act: -0.0000

Data Index: 430829 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2289. Min Act: -0.0000

Data Index: 775274 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2173. Min Act: -0.0000

Data Index: 794300 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1553780 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2099. Min Act: -0.0000

Data Index: 614255 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2100. Min Act: -0.0000

Data Index: 593251 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2160. Min Act: -0.0000

Data Index: 631555 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1036615 (C4 (Web Text))

Max Activating Token Index: 425