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

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

Neuron 355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1350. Min Act: -0.0001

Data Index: 933487 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 500319 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1431. Min Act: -0.0001

Data Index: 790570 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1040355 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1331. Min Act: -0.0001

Data Index: 501875 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1252. Min Act: -0.0001

Data Index: 579158 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1410. Min Act: -0.0000

Data Index: 433752 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1283. Min Act: -0.0001

Data Index: 28145 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1309. Min Act: -0.0001

Data Index: 361638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1313191 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1343. Min Act: -0.0001

Data Index: 692284 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1269. Min Act: -0.0001

Data Index: 414440 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1286. Min Act: -0.0001

Data Index: 484543 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1173. Min Act: -0.0001

Data Index: 203895 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1168. Min Act: -0.0001

Data Index: 356421 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1234985 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1289. Min Act: -0.0001

Data Index: 223662 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1289496 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1110. Min Act: -0.0001

Data Index: 58152 (C4 (Web Text))

Max Activating Token Index: 741