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

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

Neuron 483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.6314. Min Act: -0.0000

Data Index: 975765 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.4258. Min Act: -0.0000

Data Index: 1161239 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.5281. Min Act: -0.0000

Data Index: 790627 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3369. Min Act: -0.0000

Data Index: 905429 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3580. Min Act: -0.0000

Data Index: 416147 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3433. Min Act: -0.0000

Data Index: 1151813 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3836. Min Act: -0.0000

Data Index: 642618 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3199. Min Act: -0.0000

Data Index: 1325233 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1137334 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.1987. Min Act: -0.0000

Data Index: 19072 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.1932. Min Act: -0.0000

Data Index: 386394 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2334. Min Act: -0.0000

Data Index: 453590 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.3412. Min Act: -0.0000

Data Index: 885694 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2217. Min Act: -0.0000

Data Index: 833081 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.1529. Min Act: -0.0000

Data Index: 425378 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2864. Min Act: -0.0000

Data Index: 686177 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2193. Min Act: -0.0000

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2212. Min Act: -0.0000

Data Index: 257582 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.1946. Min Act: -0.0000

Data Index: 738471 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.6314. Min Range: -2.6314

Max Act: 2.2477. Min Act: -0.0000

Data Index: 61138 (C4 (Web Text))

Max Activating Token Index: 438