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

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

Neuron 1415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5938. Min Act: -0.0000

Data Index: 253097 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.5132. Min Act: -0.0000

Data Index: 86058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4253. Min Act: -0.0000

Data Index: 204932 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3964. Min Act: -0.0000

Data Index: 902248 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1256294 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3907. Min Act: -0.0000

Data Index: 21157 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1045339 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1211014 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3678. Min Act: -0.0000

Data Index: 225293 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3654. Min Act: -0.0000

Data Index: 706540 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3686. Min Act: -0.0000

Data Index: 215704 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3677. Min Act: -0.0000

Data Index: 768436 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1249560 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3669. Min Act: -0.0000

Data Index: 840895 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3325. Min Act: -0.0000

Data Index: 841569 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3472. Min Act: -0.0000

Data Index: 208419 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3675. Min Act: -0.0000

Data Index: 805102 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3432. Min Act: -0.0000

Data Index: 276563 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3444. Min Act: -0.0000

Data Index: 764793 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.5938. Min Range: -0.5938

Max Act: 0.3654. Min Act: -0.0000

Data Index: 615596 (C4 (Web Text))

Max Activating Token Index: 903