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

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

Neuron 2710 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: 2.5327. Min Range: -2.5327

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1218249 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 2.5327. Min Range: -2.5327

Max Act: 1.2358. Min Act: -0.0000

Data Index: 644342 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.5327. Min Range: -2.5327

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1433281 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 2.5327. Min Range: -2.5327

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1212500 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 2.5327. Min Range: -2.5327

Max Act: 1.0069. Min Act: -0.0000

Data Index: 908277 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.9711. Min Act: -0.0000

Data Index: 280719 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 2.5327. Min Range: -2.5327

Max Act: 1.0276. Min Act: -0.0000

Data Index: 49505 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.8641. Min Act: -0.0000

Data Index: 798999 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.8212. Min Act: -0.0000

Data Index: 981659 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.9918. Min Act: -0.0000

Data Index: 978007 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.9003. Min Act: -0.0000

Data Index: 740383 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1023982 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.8605. Min Act: -0.0000

Data Index: 230842 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.8272. Min Act: -0.0000

Data Index: 781930 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.9654. Min Act: -0.0000

Data Index: 197584 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.6756. Min Act: -0.0000

Data Index: 918823 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.7098. Min Act: -0.0000

Data Index: 540188 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1340670 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.7089. Min Act: -0.0000

Data Index: 95401 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.5327. Min Range: -2.5327

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1623318 (Python Code)

Max Activating Token Index: 974