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

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

Neuron 690 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: 1.7356. Min Range: -1.7356

Max Act: 1.5779. Min Act: -0.0000

Data Index: 243937 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.6289. Min Act: -0.0000

Data Index: 653377 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.5998. Min Act: -0.0000

Data Index: 151301 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.5894. Min Act: -0.0000

Data Index: 572670 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.7356. Min Act: -0.0000

Data Index: 124114 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4338. Min Act: -0.0000

Data Index: 194659 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4332. Min Act: -0.0000

Data Index: 293689 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4970. Min Act: -0.0000

Data Index: 948230 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.3962. Min Act: -0.0000

Data Index: 660396 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4614. Min Act: -0.0000

Data Index: 1022629 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4064. Min Act: -0.0000

Data Index: 922257 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4505. Min Act: -0.0000

Data Index: 497308 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.5335. Min Act: -0.0000

Data Index: 528487 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.2651. Min Act: -0.0000

Data Index: 873039 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.4278. Min Act: -0.0000

Data Index: 170321 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1445645 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.3464. Min Act: -0.0000

Data Index: 182670 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1570908 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.3232. Min Act: -0.0000

Data Index: 149565 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1392761 (Python Code)

Max Activating Token Index: 241