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

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

Neuron 1591 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4307. Min Act: -0.0001

Data Index: 18422 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1200586 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2749. Min Act: -0.0001

Data Index: 107695 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3027. Min Act: -0.0000

Data Index: 37038 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2913. Min Act: -0.0001

Data Index: 298709 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2644. Min Act: -0.0001

Data Index: 345865 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2641. Min Act: -0.0001

Data Index: 793386 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2650. Min Act: -0.0000

Data Index: 84092 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2483. Min Act: -0.0000

Data Index: 59549 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2527. Min Act: -0.0000

Data Index: 908593 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2408. Min Act: -0.0000

Data Index: 785617 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2424. Min Act: -0.0001

Data Index: 147355 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1048686 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2615. Min Act: -0.0000

Data Index: 366718 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2280. Min Act: -0.0001

Data Index: 809839 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2330. Min Act: -0.0000

Data Index: 590303 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2326. Min Act: -0.0000

Data Index: 256952 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2219. Min Act: -0.0001

Data Index: 971655 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1101070 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2294. Min Act: -0.0000

Data Index: 19041 (C4 (Web Text))

Max Activating Token Index: 940