Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1170746 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7171. Min Act: -0.0000

Data Index: 654194 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1166842 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.7398. Min Act: -0.0001

Data Index: 675549 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6733. Min Act: -0.0001

Data Index: 85479 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6671. Min Act: -0.0000

Data Index: 258331 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1116671 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6344. Min Act: -0.0001

Data Index: 1179862 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6336. Min Act: -0.0001

Data Index: 418785 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1016137 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5970. Min Act: -0.0001

Data Index: 357860 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5528. Min Act: -0.0000

Data Index: 943245 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6333. Min Act: -0.0001

Data Index: 792205 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6197. Min Act: -0.0001

Data Index: 629111 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5310. Min Act: -0.0001

Data Index: 724116 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5917. Min Act: -0.0000

Data Index: 956415 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1265976 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1398637 (Python Code)

Max Activating Token Index: 254

Text #18

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.5239. Min Act: -0.0001

Data Index: 188397 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.8522. Min Range: -0.8522

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1062907 (C4 (Web Text))

Max Activating Token Index: 372