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

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

Neuron 5053 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: 0.4605. Min Range: -0.4605

Max Act: 0.4475. Min Act: -0.0000

Data Index: 217937 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4424. Min Act: -0.0000

Data Index: 20641 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4517. Min Act: -0.0000

Data Index: 519205 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4605. Min Act: -0.0000

Data Index: 103112 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4234. Min Act: -0.0000

Data Index: 544856 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4225. Min Act: -0.0000

Data Index: 562858 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1176835 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3991. Min Act: -0.0000

Data Index: 393010 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3509. Min Act: -0.0000

Data Index: 518329 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1274069 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3517. Min Act: -0.0000

Data Index: 501497 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3596. Min Act: -0.0000

Data Index: 675909 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3621. Min Act: -0.0000

Data Index: 538199 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3077. Min Act: -0.0000

Data Index: 769571 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3013. Min Act: -0.0000

Data Index: 572056 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3019. Min Act: -0.0000

Data Index: 766682 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.2885. Min Act: -0.0000

Data Index: 409749 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.2757. Min Act: -0.0000

Data Index: 134376 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1113138 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.2927. Min Act: -0.0000

Data Index: 412384 (C4 (Web Text))

Max Activating Token Index: 870