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

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

Neuron 1757 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: 3.4282. Min Range: -3.4282

Max Act: 3.4282. Min Act: -0.0000

Data Index: 353882 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.9766. Min Act: -0.0000

Data Index: 423054 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.5335. Min Act: -0.0000

Data Index: 930093 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.6952. Min Act: -0.0000

Data Index: 626924 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3638. Min Act: -0.0000

Data Index: 542530 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3969. Min Act: -0.0000

Data Index: 169612 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3717. Min Act: -0.0000

Data Index: 945160 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1070493 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3432. Min Act: -0.0000

Data Index: 707503 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.4662. Min Act: -0.0000

Data Index: 811436 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.2246. Min Act: -0.0000

Data Index: 488001 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3448. Min Act: -0.0000

Data Index: 173199 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1294763 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3962. Min Act: -0.0000

Data Index: 306132 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.1510. Min Act: -0.0000

Data Index: 1009246 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.1472. Min Act: -0.0000

Data Index: 279650 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.1305. Min Act: -0.0000

Data Index: 733050 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.3637. Min Act: -0.0000

Data Index: 674798 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.2215. Min Act: -0.0000

Data Index: 1233596 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.4282. Min Range: -3.4282

Max Act: 2.1135. Min Act: -0.0000

Data Index: 451652 (C4 (Web Text))

Max Activating Token Index: 876