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

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

Neuron 430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: -0.0000

Data Index: 517946 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1230695 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1224607 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7674. Min Act: -0.0000

Data Index: 535540 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7605. Min Act: -0.0000

Data Index: 370789 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1369693 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7765. Min Act: -0.0000

Data Index: 807319 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7420. Min Act: -0.0000

Data Index: 745240 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7136. Min Act: -0.0000

Data Index: 9001 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7154. Min Act: -0.0000

Data Index: 966208 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7361. Min Act: -0.0000

Data Index: 277183 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7538. Min Act: -0.0000

Data Index: 746313 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7124. Min Act: 0.0000

Data Index: 863852 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1557388 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7334. Min Act: -0.0000

Data Index: 955002 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7266. Min Act: -0.0000

Data Index: 290626 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7181. Min Act: -0.0000

Data Index: 569307 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1055818 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7048. Min Act: -0.0000

Data Index: 307496 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7086. Min Act: -0.0000

Data Index: 366449 (C4 (Web Text))

Max Activating Token Index: 390