Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4852 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.6497. Min Act: -0.0000

Data Index: 175918 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1079163 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5827. Min Act: -0.0000

Data Index: 474957 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5043. Min Act: -0.0000

Data Index: 420144 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5365. Min Act: 0.0000

Data Index: 252060 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.5001. Min Act: -0.0000

Data Index: 896206 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1047633 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4748. Min Act: -0.0000

Data Index: 674121 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4655. Min Act: -0.0000

Data Index: 824774 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4897. Min Act: -0.0000

Data Index: 219082 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4712. Min Act: 0.0000

Data Index: 932076 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4518. Min Act: -0.0000

Data Index: 814903 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1184941 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4477. Min Act: -0.0000

Data Index: 58224 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4363. Min Act: -0.0000

Data Index: 892048 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4411. Min Act: -0.0000

Data Index: 654257 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4414. Min Act: -0.0000

Data Index: 312024 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4329. Min Act: -0.0000

Data Index: 93129 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4208. Min Act: -0.0000

Data Index: 944554 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.6497. Min Range: -0.6497

Max Act: 0.4332. Min Act: -0.0000

Data Index: 83851 (C4 (Web Text))

Max Activating Token Index: 381