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

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

Neuron 4355 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: 2.5427. Min Range: -2.5427

Max Act: 2.5427. Min Act: 0.0000

Data Index: 757438 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.2952. Min Act: -0.0000

Data Index: 551161 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.2093. Min Act: -0.0000

Data Index: 741752 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.2030. Min Act: -0.0000

Data Index: 922767 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0662. Min Act: 0.0000

Data Index: 665822 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1364. Min Act: 0.0000

Data Index: 941220 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1548. Min Act: -0.0000

Data Index: 479592 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1172051 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0132. Min Act: 0.0000

Data Index: 675331 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1168. Min Act: -0.0000

Data Index: 731501 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1022. Min Act: -0.0000

Data Index: 551530 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.1027. Min Act: -0.0000

Data Index: 1279120 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0834. Min Act: -0.0000

Data Index: 346039 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0647. Min Act: -0.0000

Data Index: 679353 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0461. Min Act: -0.0000

Data Index: 1341562 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0456. Min Act: -0.0000

Data Index: 1214306 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 2.5427. Min Range: -2.5427

Max Act: 2.0094. Min Act: -0.0000

Data Index: 823963 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.8817. Min Act: -0.0000

Data Index: 883260 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.7977. Min Act: -0.0000

Data Index: 1325065 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 2.5427. Min Range: -2.5427

Max Act: 1.9958. Min Act: -0.0000

Data Index: 265384 (C4 (Web Text))

Max Activating Token Index: 675