Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9309. Min Range: -2.9309

Max Act: 2.9309. Min Act: -0.0000

Data Index: 1397945 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 2.9309. Min Range: -2.9309

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1444328 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 2.9309. Min Range: -2.9309

Max Act: 2.0474. Min Act: -0.0000

Data Index: 903431 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1020053 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.9025. Min Act: -0.0000

Data Index: 1082525 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.8995. Min Act: -0.0000

Data Index: 1226958 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.8974. Min Act: -0.0000

Data Index: 1114927 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1653055 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1420933 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1540272 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.6579. Min Act: -0.0000

Data Index: 134069 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.7327. Min Act: -0.0000

Data Index: 558907 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.7435. Min Act: -0.0000

Data Index: 242206 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.6203. Min Act: -0.0000

Data Index: 263952 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1022028 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.7016. Min Act: -0.0000

Data Index: 1555661 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1601411 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.6825. Min Act: -0.0000

Data Index: 501663 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.5853. Min Act: -0.0000

Data Index: 698227 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.9309. Min Range: -2.9309

Max Act: 1.5805. Min Act: -0.0000

Data Index: 1513736 (Python Code)

Max Activating Token Index: 6