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

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

Neuron 2678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.2835. Min Act: -0.0000

Data Index: 243432 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1247361 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.1021. Min Act: -0.0000

Data Index: 158162 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1212837 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0531. Min Act: -0.0000

Data Index: 673840 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0827. Min Act: 0.0000

Data Index: 839111 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0350. Min Act: -0.0000

Data Index: 417936 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9872. Min Act: -0.0000

Data Index: 63114 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9787. Min Act: -0.0000

Data Index: 738298 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9680. Min Act: -0.0000

Data Index: 987927 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9347. Min Act: -0.0000

Data Index: 363519 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9919. Min Act: -0.0000

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9610. Min Act: -0.0000

Data Index: 358471 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1167000 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9527. Min Act: -0.0000

Data Index: 716308 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9909. Min Act: -0.0000

Data Index: 217900 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9401. Min Act: -0.0000

Data Index: 872656 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1218205 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1085839 (C4 (Web Text))

Max Activating Token Index: 965