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

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

Neuron 4230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9186. Min Range: -4.9186

Max Act: 4.9186. Min Act: -0.0000

Data Index: 1193890 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 4.9186. Min Range: -4.9186

Max Act: 4.1402. Min Act: -0.0000

Data Index: 420875 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.3411. Min Act: -0.0000

Data Index: 46157 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 4.9186. Min Range: -4.9186

Max Act: 4.7288. Min Act: -0.0000

Data Index: 45227 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.9298. Min Act: -0.0000

Data Index: 388888 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 4.9186. Min Range: -4.9186

Max Act: 4.0390. Min Act: -0.0000

Data Index: 1222357 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.3904. Min Act: -0.0000

Data Index: 981036 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.8279. Min Act: -0.0000

Data Index: 178318 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.3479. Min Act: -0.0000

Data Index: 828414 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.7155. Min Act: -0.0000

Data Index: 373735 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.9918. Min Act: -0.0000

Data Index: 1174318 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.3925. Min Act: -0.0000

Data Index: 1230426 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 4.9186. Min Range: -4.9186

Max Act: 4.4037. Min Act: -0.0000

Data Index: 206752 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.2207. Min Act: -0.0000

Data Index: 1015035 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.4408. Min Act: -0.0000

Data Index: 644541 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.5023. Min Act: -0.0000

Data Index: 1033853 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 4.9186. Min Range: -4.9186

Max Act: 3.3922. Min Act: -0.0000

Data Index: 1155933 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1226429 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.7705. Min Act: -0.0000

Data Index: 847005 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 4.9186. Min Range: -4.9186

Max Act: 2.2571. Min Act: -0.0000

Data Index: 212133 (C4 (Web Text))

Max Activating Token Index: 726