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

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

Neuron 922 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: 1.3520. Min Range: -1.3520

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1109138 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3452. Min Act: -0.0000

Data Index: 906659 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1972. Min Act: -0.0000

Data Index: 10175 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2108. Min Act: -0.0000

Data Index: 814650 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1332195 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1125580 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1185638 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1468. Min Act: -0.0000

Data Index: 189728 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1231008 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1340. Min Act: -0.0000

Data Index: 949262 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1384. Min Act: -0.0000

Data Index: 48323 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1213. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1107767 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1242631 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0983. Min Act: -0.0000

Data Index: 269145 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1098910 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1256. Min Act: -0.0000

Data Index: 81799 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0804. Min Act: -0.0000

Data Index: 817625 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1354293 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0705. Min Act: -0.0000

Data Index: 698498 (C4 (Web Text))

Max Activating Token Index: 134