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

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

Neuron 5074 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.6302. Min Act: -0.0000

Data Index: 1284906 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.3888. Min Act: -0.0000

Data Index: 88910 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.4964. Min Act: -0.0001

Data Index: 840957 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.2454. Min Act: -0.0000

Data Index: 953567 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.4502. Min Act: -0.0000

Data Index: 432855 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.1481. Min Act: -0.0000

Data Index: 225031 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.0929. Min Act: -0.0000

Data Index: 494050 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.3168. Min Act: -0.0000

Data Index: 173656 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.1773. Min Act: -0.0000

Data Index: 560362 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.9862. Min Act: -0.0000

Data Index: 716713 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.0827. Min Act: -0.0000

Data Index: 367076 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.0366. Min Act: -0.0000

Data Index: 126198 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.0218. Min Act: -0.0000

Data Index: 65426 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.7981. Min Act: -0.0000

Data Index: 496191 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.9743. Min Act: -0.0000

Data Index: 177425 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1305686 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.8457. Min Act: -0.0000

Data Index: 295634 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1244907 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.6302. Min Range: -2.6302

Max Act: 2.0218. Min Act: -0.0000

Data Index: 591987 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 2.6302. Min Range: -2.6302

Max Act: 1.8915. Min Act: -0.0000

Data Index: 1252702 (C4 (Web Text))

Max Activating Token Index: 980