Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0002

Data Index: 808445 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1550. Min Act: -0.0002

Data Index: 710074 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1555. Min Act: -0.0002

Data Index: 1128102 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1502. Min Act: -0.0002

Data Index: 151810 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1185834 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1436. Min Act: -0.0002

Data Index: 76427 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1371. Min Act: -0.0002

Data Index: 1207025 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1416. Min Act: -0.0002

Data Index: 882316 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1374. Min Act: -0.0002

Data Index: 614923 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1268043 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1257106 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1284. Min Act: -0.0002

Data Index: 984994 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1306. Min Act: -0.0002

Data Index: 477419 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1317. Min Act: -0.0002

Data Index: 113169 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1352. Min Act: -0.0002

Data Index: 250849 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1242. Min Act: -0.0002

Data Index: 836639 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1275. Min Act: -0.0002

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1327. Min Act: -0.0002

Data Index: 98151 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1278. Min Act: -0.0002

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1288. Min Act: -0.0002

Data Index: 68338 (C4 (Web Text))

Max Activating Token Index: 707