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

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

Neuron 4419 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6965. Min Act: -0.0000

Data Index: 960033 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1278481 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6204. Min Act: -0.0000

Data Index: 675345 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6120. Min Act: -0.0000

Data Index: 142150 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6511. Min Act: -0.0000

Data Index: 877318 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1051105 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5697. Min Act: -0.0000

Data Index: 526797 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1343838 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5272. Min Act: -0.0000

Data Index: 905573 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5759. Min Act: -0.0000

Data Index: 304246 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5619. Min Act: -0.0000

Data Index: 569208 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5478. Min Act: -0.0000

Data Index: 722958 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5326. Min Act: -0.0000

Data Index: 593960 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4968. Min Act: -0.0000

Data Index: 295230 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5141. Min Act: -0.0000

Data Index: 95754 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4365. Min Act: -0.0000

Data Index: 530153 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4973. Min Act: -0.0000

Data Index: 440524 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.4932. Min Act: -0.0000

Data Index: 987451 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5026. Min Act: -0.0000

Data Index: 828583 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1028579 (C4 (Web Text))

Max Activating Token Index: 423