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

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

Neuron 99 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1247168 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1297612 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1249028 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.3363. Min Act: -0.0000

Data Index: 987399 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1316668 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.2721. Min Act: -0.0000

Data Index: 502980 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.2667. Min Act: -0.0000

Data Index: 412031 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.1530. Min Act: -0.0000

Data Index: 427452 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.1775. Min Act: -0.0000

Data Index: 214759 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.0900. Min Act: -0.0000

Data Index: 415264 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.1485. Min Act: -0.0000

Data Index: 573582 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.0740. Min Act: -0.0000

Data Index: 406205 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1138376 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.1234. Min Act: -0.0000

Data Index: 806115 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1298473 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.5018. Min Range: -1.5018

Max Act: 0.9803. Min Act: -0.0000

Data Index: 705633 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.0910. Min Act: -0.0000

Data Index: 691789 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.0689. Min Act: -0.0000

Data Index: 509149 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.5018. Min Range: -1.5018

Max Act: 1.0780. Min Act: -0.0000

Data Index: 560397 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.5018. Min Range: -1.5018

Max Act: 0.9981. Min Act: -0.0000

Data Index: 214667 (C4 (Web Text))

Max Activating Token Index: 316