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

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

Neuron 3766 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: 1.1925. Min Range: -1.1925

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1203657 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1925. Min Act: -0.0001

Data Index: 659899 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1797. Min Act: -0.0001

Data Index: 475967 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1060. Min Act: -0.0001

Data Index: 873430 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1440014 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1307. Min Act: -0.0001

Data Index: 580316 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0050. Min Act: -0.0001

Data Index: 150662 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0946. Min Act: -0.0001

Data Index: 359176 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1068114 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0195. Min Act: -0.0000

Data Index: 46536 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0139. Min Act: -0.0001

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1484. Min Act: -0.0000

Data Index: 828568 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0393. Min Act: -0.0001

Data Index: 848919 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0036. Min Act: -0.0001

Data Index: 565634 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0352. Min Act: -0.0001

Data Index: 238903 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.0335. Min Act: -0.0001

Data Index: 1259343 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9713. Min Act: -0.0001

Data Index: 1259944 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9882. Min Act: -0.0001

Data Index: 438416 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9138. Min Act: -0.0001

Data Index: 146490 (C4 (Web Text))

Max Activating Token Index: 838