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

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

Neuron 4536 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1352878 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9354. Min Act: -0.0000

Data Index: 189236 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9729. Min Act: -0.0000

Data Index: 609710 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9552. Min Act: -0.0000

Data Index: 663400 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7484. Min Act: -0.0000

Data Index: 750166 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7920. Min Act: -0.0000

Data Index: 184563 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7596. Min Act: -0.0000

Data Index: 840552 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1191937 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6498. Min Act: -0.0000

Data Index: 116263 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1072994 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6845. Min Act: -0.0000

Data Index: 370349 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7496. Min Act: -0.0000

Data Index: 155488 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7388. Min Act: -0.0000

Data Index: 277045 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1247076 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6404. Min Act: -0.0000

Data Index: 312212 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1072711 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1043272 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1180265 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.5954. Min Act: -0.0000

Data Index: 135555 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.6342. Min Act: -0.0000

Data Index: 297082 (C4 (Web Text))

Max Activating Token Index: 382