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

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

Neuron 3619 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1489. Min Act: -0.0001

Data Index: 915501 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1490. Min Act: -0.0001

Data Index: 623500 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1475. Min Act: -0.0001

Data Index: 274460 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1378. Min Act: -0.0001

Data Index: 861350 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1369. Min Act: -0.0001

Data Index: 250226 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1185562 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1345. Min Act: -0.0001

Data Index: 164023 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1041347 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1330. Min Act: -0.0001

Data Index: 106502 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1243. Min Act: -0.0001

Data Index: 608985 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1261. Min Act: -0.0001

Data Index: 781184 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1274. Min Act: -0.0001

Data Index: 396457 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1249. Min Act: -0.0001

Data Index: 110950 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1201. Min Act: -0.0001

Data Index: 687183 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1230. Min Act: -0.0001

Data Index: 67824 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1288. Min Act: -0.0001

Data Index: 933732 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1178. Min Act: -0.0001

Data Index: 2842 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1294. Min Act: -0.0001

Data Index: 930134 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1216. Min Act: -0.0001

Data Index: 429207 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1201. Min Act: -0.0001

Data Index: 394839 (C4 (Web Text))

Max Activating Token Index: 524