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

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

Neuron 1729 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4667. Min Act: -0.0000

Data Index: 146049 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4800. Min Act: -0.0000

Data Index: 465063 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1172630 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4371. Min Act: -0.0000

Data Index: 402938 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4405. Min Act: -0.0000

Data Index: 265139 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1341641 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4302. Min Act: -0.0000

Data Index: 672211 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4096. Min Act: -0.0000

Data Index: 475851 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3969. Min Act: -0.0000

Data Index: 429539 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4199. Min Act: -0.0000

Data Index: 763293 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4296. Min Act: -0.0000

Data Index: 696095 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4063. Min Act: -0.0000

Data Index: 264325 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3761. Min Act: -0.0000

Data Index: 338858 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3818. Min Act: -0.0000

Data Index: 232568 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4093. Min Act: -0.0000

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3611. Min Act: -0.0000

Data Index: 234478 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4039. Min Act: -0.0000

Data Index: 144235 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3729. Min Act: -0.0000

Data Index: 99816 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3696. Min Act: -0.0000

Data Index: 952276 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1113558 (C4 (Web Text))

Max Activating Token Index: 172