Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3660. Min Act: -0.0001

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3418. Min Act: -0.0002

Data Index: 463459 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3472. Min Act: -0.0001

Data Index: 378486 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3384. Min Act: -0.0001

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3475. Min Act: -0.0001

Data Index: 767395 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3467. Min Act: -0.0002

Data Index: 682067 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1211488 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3326. Min Act: -0.0002

Data Index: 406390 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1035402 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3375. Min Act: -0.0002

Data Index: 408676 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3061. Min Act: -0.0001

Data Index: 62151 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3087. Min Act: -0.0001

Data Index: 232865 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3314. Min Act: -0.0001

Data Index: 702545 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2992. Min Act: -0.0002

Data Index: 257063 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2977. Min Act: -0.0001

Data Index: 53861 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3260. Min Act: -0.0002

Data Index: 431851 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3100. Min Act: -0.0002

Data Index: 323552 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3038. Min Act: -0.0001

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1153344 (C4 (Web Text))

Max Activating Token Index: 10