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

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

Neuron 1566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: -0.0002

Data Index: 191 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5995. Min Act: -0.0002

Data Index: 131641 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6775. Min Act: -0.0002

Data Index: 1020860 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5496. Min Act: -0.0002

Data Index: 61669 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5539. Min Act: -0.0002

Data Index: 1585066 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6059. Min Act: -0.0002

Data Index: 1164199 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5695. Min Act: -0.0002

Data Index: 1198884 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.6166. Min Act: -0.0002

Data Index: 810453 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5847. Min Act: -0.0002

Data Index: 144104 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5819. Min Act: -0.0002

Data Index: 728053 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5269. Min Act: -0.0002

Data Index: 584963 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4917. Min Act: -0.0002

Data Index: 1133796 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5181. Min Act: -0.0002

Data Index: 1200796 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5608. Min Act: -0.0002

Data Index: 1014270 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4938. Min Act: -0.0002

Data Index: 944831 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5176. Min Act: -0.0002

Data Index: 1641856 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5250. Min Act: -0.0002

Data Index: 1055089 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5404. Min Act: -0.0002

Data Index: 160706 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5044. Min Act: -0.0002

Data Index: 1197443 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5438. Min Act: -0.0002

Data Index: 1025041 (C4 (Web Text))

Max Activating Token Index: 246