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

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

Neuron 338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1173195 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4408. Min Act: -0.0001

Data Index: 235704 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4750. Min Act: -0.0001

Data Index: 158545 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4541. Min Act: -0.0001

Data Index: 275712 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4246. Min Act: -0.0001

Data Index: 978446 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1294114 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3815. Min Act: -0.0000

Data Index: 918215 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1190489 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1235431 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1285046 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3727. Min Act: -0.0000

Data Index: 269286 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1001351 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3202. Min Act: -0.0000

Data Index: 163518 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3340. Min Act: -0.0000

Data Index: 529338 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3513. Min Act: -0.0001

Data Index: 1026831 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1323782 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3062. Min Act: -0.0001

Data Index: 114463 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1537839 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1577885 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3095. Min Act: -0.0001

Data Index: 1041478 (C4 (Web Text))

Max Activating Token Index: 613