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

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

Neuron 3812 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1602780 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4314. Min Act: -0.0000

Data Index: 484588 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4302. Min Act: -0.0000

Data Index: 656710 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1451544 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4011. Min Act: -0.0000

Data Index: 455888 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3927. Min Act: -0.0000

Data Index: 165981 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1596293 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3458. Min Act: -0.0000

Data Index: 9885 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3560. Min Act: -0.0000

Data Index: 460542 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1571692 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1527037 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3967. Min Act: -0.0000

Data Index: 343229 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1257022 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3422. Min Act: -0.0000

Data Index: 117306 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1294946 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2939. Min Act: -0.0000

Data Index: 652199 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2590. Min Act: -0.0000

Data Index: 145209 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1008926 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1589278 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.2885. Min Act: -0.0000

Data Index: 138131 (C4 (Web Text))

Max Activating Token Index: 998