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

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

Neuron 5371 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1112156 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.1365. Min Act: -0.0000

Data Index: 507603 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0501. Min Act: -0.0000

Data Index: 751767 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.1169. Min Act: -0.0000

Data Index: 949851 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.1743. Min Act: -0.0000

Data Index: 236819 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1322836 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9418. Min Act: 0.0000

Data Index: 998781 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1195804 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1326506 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8844. Min Act: -0.0000

Data Index: 879632 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8780. Min Act: -0.0000

Data Index: 342536 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9204. Min Act: -0.0000

Data Index: 889492 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9128. Min Act: -0.0000

Data Index: 555022 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9086. Min Act: -0.0000

Data Index: 193704 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8405. Min Act: -0.0000

Data Index: 575223 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.7922. Min Act: -0.0000

Data Index: 106214 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8910. Min Act: -0.0000

Data Index: 639875 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8283. Min Act: -0.0000

Data Index: 714118 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9325. Min Act: -0.0000

Data Index: 663011 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1323090 (C4 (Web Text))

Max Activating Token Index: 599