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

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

Neuron 1995 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: 0.5538. Min Range: -0.5538

Max Act: 0.5037. Min Act: -0.0000

Data Index: 67329 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5538. Min Act: -0.0000

Data Index: 499763 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1209765 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4325. Min Act: -0.0000

Data Index: 617303 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4590. Min Act: -0.0000

Data Index: 446862 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4262. Min Act: -0.0000

Data Index: 774933 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4197. Min Act: -0.0000

Data Index: 778639 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4053. Min Act: -0.0000

Data Index: 902532 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4343. Min Act: -0.0000

Data Index: 508266 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3585. Min Act: -0.0000

Data Index: 752720 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4051. Min Act: -0.0000

Data Index: 373047 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3699. Min Act: -0.0000

Data Index: 778622 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3758. Min Act: -0.0000

Data Index: 81210 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1212958 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3897. Min Act: -0.0000

Data Index: 565289 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3849. Min Act: -0.0000

Data Index: 23060 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3707. Min Act: -0.0000

Data Index: 285412 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4006. Min Act: -0.0000

Data Index: 866522 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3759. Min Act: -0.0000

Data Index: 313950 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3279. Min Act: -0.0000

Data Index: 406846 (C4 (Web Text))

Max Activating Token Index: 135