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

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

Neuron 1648 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: 0.7765. Min Range: -0.7765

Max Act: 0.7097. Min Act: -0.0000

Data Index: 151719 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7765. Min Act: -0.0001

Data Index: 764969 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1065010 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1415263 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6845. Min Act: -0.0000

Data Index: 826644 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6205. Min Act: -0.0000

Data Index: 764195 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1061712 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1428021 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5600. Min Act: -0.0000

Data Index: 961592 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6109. Min Act: -0.0000

Data Index: 182852 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5869. Min Act: -0.0000

Data Index: 211418 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1233271 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5371. Min Act: -0.0001

Data Index: 1149714 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1586291 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5467. Min Act: -0.0000

Data Index: 850741 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1212884 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1209263 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5510. Min Act: -0.0000

Data Index: 144461 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.4974. Min Act: -0.0000

Data Index: 649274 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1575362 (Python Code)

Max Activating Token Index: 205