Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1983 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1978. Min Range: -1.1978

Max Act: 1.1978. Min Act: -0.0000

Data Index: 199521 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8840. Min Act: -0.0000

Data Index: 619247 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8103. Min Act: -0.0000

Data Index: 94360 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7247. Min Act: -0.0000

Data Index: 591154 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7651. Min Act: -0.0000

Data Index: 936651 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7418. Min Act: -0.0000

Data Index: 264445 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7444. Min Act: -0.0000

Data Index: 720568 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7167. Min Act: -0.0000

Data Index: 978761 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7812. Min Act: -0.0000

Data Index: 877378 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1282169 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6367. Min Act: -0.0000

Data Index: 897300 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6796. Min Act: -0.0000

Data Index: 652017 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6770. Min Act: -0.0000

Data Index: 709930 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1226061 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1014643 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6145. Min Act: -0.0000

Data Index: 112116 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1202943 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1161919 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.5653. Min Act: -0.0000

Data Index: 892069 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.5695. Min Act: -0.0000

Data Index: 143696 (C4 (Web Text))

Max Activating Token Index: 479