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

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

Neuron 2848 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1155083 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.9260. Min Act: -0.0000

Data Index: 130394 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.8127. Min Act: -0.0000

Data Index: 578195 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.8013. Min Act: -0.0000

Data Index: 423268 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7613. Min Act: -0.0000

Data Index: 506586 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7722. Min Act: -0.0000

Data Index: 644584 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7265. Min Act: -0.0000

Data Index: 598806 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1313773 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7172. Min Act: -0.0000

Data Index: 192936 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6531. Min Act: -0.0000

Data Index: 127017 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6747. Min Act: -0.0000

Data Index: 420568 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6734. Min Act: 0.0000

Data Index: 933283 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1234061 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7514. Min Act: -0.0000

Data Index: 973689 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7382. Min Act: -0.0000

Data Index: 149312 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6828. Min Act: -0.0000

Data Index: 30960 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6747. Min Act: -0.0000

Data Index: 863498 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1278114 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.9260. Min Range: -0.9260

Max Act: 0.6841. Min Act: -0.0000

Data Index: 264230 (C4 (Web Text))

Max Activating Token Index: 158