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

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

Neuron 2594 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.5468. Min Act: -0.0000

Data Index: 386378 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3976. Min Act: -0.0000

Data Index: 209617 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1188096 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.4336. Min Act: -0.0000

Data Index: 404272 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.4937. Min Act: -0.0000

Data Index: 98749 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1257351 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3034. Min Act: -0.0000

Data Index: 253236 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3677. Min Act: -0.0000

Data Index: 365800 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3315. Min Act: -0.0000

Data Index: 289662 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2403. Min Act: -0.0000

Data Index: 800333 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2490. Min Act: -0.0000

Data Index: 865751 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2988. Min Act: -0.0000

Data Index: 600022 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3667. Min Act: -0.0000

Data Index: 435729 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3491. Min Act: -0.0000

Data Index: 819573 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2690. Min Act: -0.0000

Data Index: 153920 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2642. Min Act: -0.0000

Data Index: 905361 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2547. Min Act: 0.0000

Data Index: 1347003 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1003102 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.1701. Min Act: -0.0000

Data Index: 961680 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.2245. Min Act: -0.0000

Data Index: 268148 (C4 (Web Text))

Max Activating Token Index: 213