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

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

Neuron 4955 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: 0.5480. Min Range: -0.5480

Max Act: 0.5480. Min Act: -0.0000

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4185. Min Act: -0.0000

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3961. Min Act: -0.0000

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3650. Min Act: -0.0000

Data Index: 601757 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3805. Min Act: -0.0000

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3863. Min Act: -0.0000

Data Index: 570442 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4073. Min Act: -0.0000

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3669. Min Act: -0.0000

Data Index: 79053 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3580. Min Act: -0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3529. Min Act: -0.0000

Data Index: 828973 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3419. Min Act: -0.0000

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1335325 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3091. Min Act: -0.0000

Data Index: 496075 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3321. Min Act: -0.0000

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.2931. Min Act: -0.0000

Data Index: 477323 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1159766 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.2628. Min Act: -0.0000

Data Index: 408993 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.2258. Min Act: -0.0000

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 860