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

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

Neuron 4138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.8110. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.9957. Min Act: -0.0000

Data Index: 919662 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.6610. Min Act: -0.0001

Data Index: 1164891 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.5625. Min Act: -0.0001

Data Index: 1124808 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.5149. Min Act: -0.0000

Data Index: 82806 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.5842. Min Act: -0.0000

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.5467. Min Act: -0.0001

Data Index: 813054 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.4320. Min Act: -0.0000

Data Index: 58312 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.2626. Min Act: -0.0001

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.4213. Min Act: -0.0001

Data Index: 1195141 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.4149. Min Act: -0.0001

Data Index: 1031956 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.4154. Min Act: -0.0001

Data Index: 221685 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.4139. Min Act: -0.0001

Data Index: 242848 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.3157. Min Act: -0.0000

Data Index: 522858 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.2922. Min Act: -0.0001

Data Index: 416390 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.2723. Min Act: -0.0001

Data Index: 435680 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.3100. Min Act: -0.0000

Data Index: 569063 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.2792. Min Act: -0.0001

Data Index: 1350635 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.2452. Min Act: -0.0001

Data Index: 204403 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.9957. Min Range: -1.9957

Max Act: 1.3265. Min Act: -0.0000

Data Index: 119370 (C4 (Web Text))

Max Activating Token Index: 246