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

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

Neuron 3300 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: 0.7735. Min Range: -0.7735

Max Act: 0.7735. Min Act: -0.0000

Data Index: 439096 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7454. Min Act: -0.0000

Data Index: 57396 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6956. Min Act: -0.0000

Data Index: 470994 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6616. Min Act: -0.0000

Data Index: 980648 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1200193 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6674. Min Act: -0.0000

Data Index: 81780 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6232. Min Act: -0.0000

Data Index: 515935 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6246. Min Act: -0.0000

Data Index: 227118 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1332200 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6130. Min Act: -0.0000

Data Index: 684912 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5835. Min Act: -0.0000

Data Index: 921039 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6018. Min Act: -0.0000

Data Index: 495050 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5701. Min Act: -0.0000

Data Index: 446539 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5325. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5631. Min Act: -0.0000

Data Index: 926502 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5600. Min Act: -0.0000

Data Index: 51769 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5884. Min Act: -0.0000

Data Index: 735820 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5801. Min Act: 0.0000

Data Index: 885439 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5717. Min Act: -0.0000

Data Index: 43482 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5365. Min Act: 0.0000

Data Index: 352284 (C4 (Web Text))

Max Activating Token Index: 536