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

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

Neuron 604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6025. Min Act: -0.0001

Data Index: 687010 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6597. Min Act: -0.0001

Data Index: 293001 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6485. Min Act: -0.0000

Data Index: 521692 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5934. Min Act: -0.0001

Data Index: 1259292 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5840. Min Act: -0.0000

Data Index: 437173 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5562. Min Act: -0.0000

Data Index: 274722 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5932. Min Act: -0.0000

Data Index: 171000 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5268. Min Act: -0.0000

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1043545 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5690. Min Act: -0.0000

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4553. Min Act: -0.0000

Data Index: 58891 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4957. Min Act: -0.0000

Data Index: 827772 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5125. Min Act: -0.0001

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5223. Min Act: -0.0000

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4998. Min Act: -0.0001

Data Index: 1083797 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4252. Min Act: -0.0000

Data Index: 297176 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5176. Min Act: -0.0000

Data Index: 370994 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1228981 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4661. Min Act: -0.0000

Data Index: 130952 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5129. Min Act: -0.0000

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 507