Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.8755. Min Act: -0.0001

Data Index: 783870 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.7690. Min Act: -0.0001

Data Index: 885129 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6502. Min Act: -0.0001

Data Index: 533574 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6622. Min Act: -0.0001

Data Index: 222995 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5531. Min Act: -0.0001

Data Index: 864621 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6281. Min Act: -0.0001

Data Index: 406728 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5968. Min Act: -0.0001

Data Index: 223721 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.6126. Min Act: -0.0001

Data Index: 167091 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5279. Min Act: -0.0001

Data Index: 936068 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5878. Min Act: -0.0001

Data Index: 868375 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5893. Min Act: -0.0001

Data Index: 14489 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5486. Min Act: -0.0001

Data Index: 320501 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5346. Min Act: -0.0001

Data Index: 1331613 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5316. Min Act: -0.0001

Data Index: 359094 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1065565 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1155749 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.4973. Min Act: -0.0001

Data Index: 611010 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5112. Min Act: -0.0001

Data Index: 362311 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1112640 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.8755. Min Range: -0.8755

Max Act: 0.5076. Min Act: -0.0001

Data Index: 1155312 (C4 (Web Text))

Max Activating Token Index: 835