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

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

Neuron 622 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.7639. Min Act: -0.0000

Data Index: 1165650 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.8651. Min Act: -0.0000

Data Index: 917335 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.7414. Min Act: -0.0000

Data Index: 1104786 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.6403. Min Act: -0.0000

Data Index: 76908 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1099003 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1312489 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.5526. Min Act: -0.0000

Data Index: 708063 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.4029. Min Act: -0.0000

Data Index: 433002 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1010330 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.4346. Min Act: -0.0000

Data Index: 807801 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.4160. Min Act: -0.0000

Data Index: 230680 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.3514. Min Act: -0.0000

Data Index: 337700 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1164834 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.3199. Min Act: -0.0000

Data Index: 335168 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.2650. Min Act: -0.0000

Data Index: 637002 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.2641. Min Act: -0.0000

Data Index: 349250 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.2319. Min Act: -0.0000

Data Index: 998980 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.1975. Min Act: -0.0000

Data Index: 635947 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.1286. Min Act: -0.0000

Data Index: 492614 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 1.8651. Min Range: -1.8651

Max Act: 1.1893. Min Act: -0.0000

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 540