Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 45 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.7152. Min Act: -0.0000

Data Index: 827113 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.8440. Min Act: -0.0001

Data Index: 103711 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.7882. Min Act: -0.0000

Data Index: 467897 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1346212 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6680. Min Act: -0.0000

Data Index: 125831 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6488. Min Act: -0.0001

Data Index: 240056 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6001. Min Act: -0.0000

Data Index: 172436 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6835. Min Act: -0.0000

Data Index: 614045 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3454. Min Act: -0.0000

Data Index: 973818 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6802. Min Act: -0.0000

Data Index: 803506 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6683. Min Act: -0.0000

Data Index: 659694 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.7659. Min Act: -0.0000

Data Index: 409747 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4694. Min Act: -0.0000

Data Index: 339977 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5524. Min Act: -0.0000

Data Index: 848930 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6979. Min Act: -0.0000

Data Index: 283690 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4872. Min Act: -0.0000

Data Index: 59385 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4838. Min Act: -0.0000

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4725. Min Act: -0.0000

Data Index: 1119130 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4319. Min Act: -0.0000

Data Index: 482751 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4428. Min Act: -0.0000

Data Index: 889939 (C4 (Web Text))

Max Activating Token Index: 575