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

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

Neuron 3612 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: 2.5575. Min Range: -2.5575

Max Act: 2.5575. Min Act: -0.0000

Data Index: 1650597 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 2.5575. Min Range: -2.5575

Max Act: 2.4325. Min Act: -0.0000

Data Index: 1415138 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.9969. Min Act: -0.0000

Data Index: 1511170 (Python Code)

Max Activating Token Index: 245

Text #3

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.6819. Min Act: -0.0000

Data Index: 1374506 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1433519 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7498. Min Act: -0.0000

Data Index: 1447256 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1587614 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7152. Min Act: -0.0000

Data Index: 1548054 (Python Code)

Max Activating Token Index: 772

Text #8

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1445229 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.6523. Min Act: -0.0000

Data Index: 1410119 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5275. Min Act: -0.0000

Data Index: 1545151 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1458449 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1538343 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1482816 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1604437 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1576848 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1542329 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1368347 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7447. Min Act: -0.0000

Data Index: 1531271 (Python Code)

Max Activating Token Index: 646

Text #19

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.5425. Min Act: -0.0000

Data Index: 1369775 (Python Code)

Max Activating Token Index: 624