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

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

Neuron 1387 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: 3.3317. Min Range: -3.3317

Max Act: 3.3317. Min Act: -0.0000

Data Index: 322775 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.9406. Min Act: -0.0000

Data Index: 226398 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.7591. Min Act: -0.0000

Data Index: 873639 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.9171. Min Act: -0.0000

Data Index: 379739 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.9807. Min Act: -0.0000

Data Index: 316258 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.9595. Min Act: -0.0000

Data Index: 342727 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.6203. Min Act: -0.0000

Data Index: 1265421 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.7192. Min Act: -0.0000

Data Index: 635336 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.7363. Min Act: -0.0000

Data Index: 238655 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.5834. Min Act: -0.0000

Data Index: 240502 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.6763. Min Act: 0.0001

Data Index: 898646 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.6355. Min Act: -0.0000

Data Index: 387795 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.7591. Min Act: -0.0000

Data Index: 1224498 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.3536. Min Act: -0.0000

Data Index: 50551 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.5772. Min Act: -0.0000

Data Index: 38980 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.8345. Min Act: -0.0000

Data Index: 485703 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.4977. Min Act: -0.0000

Data Index: 823629 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.5178. Min Act: -0.0000

Data Index: 365275 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.4534. Min Act: -0.0000

Data Index: 753708 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.3317. Min Range: -3.3317

Max Act: 2.5725. Min Act: -0.0000

Data Index: 1006176 (C4 (Web Text))

Max Activating Token Index: 141