Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0687. Min Act: -0.0002

Data Index: 340932 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1228. Min Act: -0.0001

Data Index: 402172 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0961. Min Act: -0.0002

Data Index: 1061798 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.2321. Min Act: -0.0002

Data Index: 800628 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.9100. Min Act: -0.0001

Data Index: 1057610 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.9517. Min Act: -0.0002

Data Index: 867240 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.9436. Min Act: -0.0001

Data Index: 803184 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.5850. Min Act: -0.0001

Data Index: 639531 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.4919. Min Act: -0.0002

Data Index: 916339 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.4129. Min Act: -0.0002

Data Index: 155941 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.5180. Min Act: -0.0002

Data Index: 535166 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.3797. Min Act: -0.0001

Data Index: 173276 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.1973. Min Act: -0.0002

Data Index: 1355390 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.1652. Min Act: -0.0002

Data Index: 608040 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.3229. Min Act: -0.0001

Data Index: 524263 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.4060. Min Act: -0.0002

Data Index: 912778 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.2947. Min Act: -0.0001

Data Index: 1221338 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.4427. Min Act: -0.0002

Data Index: 181215 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.3425. Min Act: -0.0001

Data Index: 1334190 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.2321. Min Range: -3.2321

Max Act: 2.1385. Min Act: -0.0001

Data Index: 876817 (C4 (Web Text))

Max Activating Token Index: 466