Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4095 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1289450 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0001

Data Index: 384651 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0001

Data Index: 535199 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0283. Min Act: -0.0001

Data Index: 516439 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0260. Min Act: -0.0001

Data Index: 538018 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0263. Min Act: -0.0001

Data Index: 345106 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0250. Min Act: -0.0001

Data Index: 165111 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0001

Data Index: 992810 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0001

Data Index: 619018 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0242. Min Act: -0.0001

Data Index: 101489 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0251. Min Act: -0.0001

Data Index: 575694 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0237. Min Act: -0.0001

Data Index: 711911 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0259. Min Act: -0.0001

Data Index: 604304 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1069201 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0236. Min Act: -0.0001

Data Index: 70905 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1483378 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0231. Min Act: -0.0001

Data Index: 483600 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1148991 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0231. Min Act: -0.0001

Data Index: 415918 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0240. Min Act: -0.0001

Data Index: 387039 (C4 (Web Text))

Max Activating Token Index: 192