Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4182 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0957. Min Range: -2.0957

Max Act: 2.0957. Min Act: -0.0000

Data Index: 478393 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.7069. Min Act: -0.0000

Data Index: 640970 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.6435. Min Act: -0.0000

Data Index: 345286 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1322087 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1112811 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3887. Min Act: -0.0000

Data Index: 87058 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4415. Min Act: -0.0000

Data Index: 1327063 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1043742 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3808. Min Act: -0.0000

Data Index: 969055 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4402. Min Act: -0.0000

Data Index: 372388 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3767. Min Act: -0.0000

Data Index: 244755 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4270. Min Act: -0.0000

Data Index: 191301 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3447. Min Act: -0.0000

Data Index: 32364 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3571. Min Act: -0.0000

Data Index: 100021 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.4093. Min Act: -0.0000

Data Index: 937955 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1107405 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3237. Min Act: -0.0000

Data Index: 267737 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.3128. Min Act: -0.0000

Data Index: 929653 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1084841 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 2.0957. Min Range: -2.0957

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1298284 (C4 (Web Text))

Max Activating Token Index: 677