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

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

Neuron 840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.1357. Min Act: -0.0001

Data Index: 1209955 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.1677. Min Act: -0.0001

Data Index: 876941 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0504. Min Act: -0.0001

Data Index: 459636 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9100. Min Act: -0.0001

Data Index: 138638 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9911. Min Act: -0.0001

Data Index: 1220057 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0355. Min Act: -0.0001

Data Index: 250427 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9591. Min Act: -0.0001

Data Index: 643727 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9293. Min Act: -0.0001

Data Index: 959989 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9146. Min Act: -0.0001

Data Index: 521235 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1349034 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9029. Min Act: -0.0001

Data Index: 966916 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8533. Min Act: -0.0001

Data Index: 357576 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8869. Min Act: -0.0001

Data Index: 509024 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8787. Min Act: -0.0001

Data Index: 425336 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8360. Min Act: -0.0001

Data Index: 282269 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7451. Min Act: -0.0001

Data Index: 239691 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7803. Min Act: -0.0001

Data Index: 308623 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7944. Min Act: -0.0001

Data Index: 575691 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7376. Min Act: -0.0001

Data Index: 274396 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7729. Min Act: -0.0001

Data Index: 509337 (C4 (Web Text))

Max Activating Token Index: 664