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

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

Neuron 3195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0624. Min Act: -0.0000

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1107087 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1020233 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9976. Min Act: -0.0000

Data Index: 568017 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1247472 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0245. Min Act: -0.0000

Data Index: 514361 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0018. Min Act: -0.0000

Data Index: 510921 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1142177 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9917. Min Act: -0.0000

Data Index: 144402 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9704. Min Act: -0.0000

Data Index: 781476 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9342. Min Act: -0.0000

Data Index: 731096 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9468. Min Act: -0.0000

Data Index: 847608 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9467. Min Act: -0.0000

Data Index: 215654 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1204649 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9120. Min Act: -0.0000

Data Index: 586756 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1394383 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1111209 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9286. Min Act: -0.0000

Data Index: 47154 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9343. Min Act: -0.0000

Data Index: 447823 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1002527 (C4 (Web Text))

Max Activating Token Index: 545