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

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

Neuron 5589 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1520. Min Act: -0.0000

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1319. Min Act: -0.0000

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1372. Min Act: -0.0000

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1267. Min Act: -0.0000

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1197. Min Act: -0.0000

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1275. Min Act: -0.0000

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1257. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1293. Min Act: -0.0000

Data Index: 901532 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1275. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1199. Min Act: -0.0000

Data Index: 583112 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1215. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1068. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1318632 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0967. Min Act: -0.0000

Data Index: 623474 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0941. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1429600 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.0946. Min Act: -0.0000

Data Index: 724525 (C4 (Web Text))

Max Activating Token Index: 76