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

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

Neuron 1380 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: 5.3448. Min Range: -5.3448

Max Act: 5.3448. Min Act: -0.0000

Data Index: 305987 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.8876. Min Act: -0.0000

Data Index: 680603 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.3475. Min Act: -0.0000

Data Index: 761547 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.6187. Min Act: -0.0000

Data Index: 685685 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.3089. Min Act: -0.0000

Data Index: 1170885 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.0970. Min Act: -0.0000

Data Index: 824668 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.0433. Min Act: -0.0000

Data Index: 642781 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.8438. Min Act: -0.0000

Data Index: 113683 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.9724. Min Act: -0.0000

Data Index: 359974 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.0735. Min Act: -0.0000

Data Index: 1206708 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.9027. Min Act: -0.0000

Data Index: 1334194 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.8581. Min Act: -0.0000

Data Index: 900420 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.8801. Min Act: -0.0000

Data Index: 759151 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.4445. Min Act: -0.0000

Data Index: 873374 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 5.3448. Min Range: -5.3448

Max Act: 4.0466. Min Act: -0.0000

Data Index: 562683 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.4311. Min Act: -0.0000

Data Index: 171569 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.3948. Min Act: -0.0000

Data Index: 1150363 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.4302. Min Act: -0.0000

Data Index: 1200884 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.2854. Min Act: -0.0000

Data Index: 815478 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 5.3448. Min Range: -5.3448

Max Act: 3.6020. Min Act: -0.0000

Data Index: 98521 (C4 (Web Text))

Max Activating Token Index: 499