Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.9307. Min Act: -0.0000

Data Index: 246397 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.6788. Min Act: -0.0000

Data Index: 396155 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.7257. Min Act: -0.0000

Data Index: 252971 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.6543. Min Act: -0.0001

Data Index: 1222696 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.7363. Min Act: -0.0000

Data Index: 737761 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.6962. Min Act: -0.0000

Data Index: 1268024 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.5761. Min Act: -0.0000

Data Index: 1010883 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.5205. Min Act: -0.0001

Data Index: 761482 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.5891. Min Act: -0.0000

Data Index: 187954 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4789. Min Act: -0.0000

Data Index: 952576 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3840. Min Act: -0.0000

Data Index: 300552 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4286. Min Act: -0.0000

Data Index: 1233499 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3404. Min Act: -0.0001

Data Index: 669306 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4001. Min Act: -0.0000

Data Index: 64584 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3596. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2653. Min Act: -0.0001

Data Index: 1231851 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2530. Min Act: -0.0000

Data Index: 169675 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2924. Min Act: -0.0000

Data Index: 994586 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3805. Min Act: -0.0000

Data Index: 507021 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.1497. Min Act: -0.0000

Data Index: 1215336 (C4 (Web Text))

Max Activating Token Index: 117