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

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

Neuron 157 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: 2.4274. Min Range: -2.4274

Max Act: 2.1931. Min Act: -0.0000

Data Index: 1417074 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.3548. Min Act: -0.0000

Data Index: 1500101 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1442638 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.4274. Min Act: -0.0000

Data Index: 1564059 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.2198. Min Act: -0.0000

Data Index: 1508674 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.4104. Min Act: -0.0000

Data Index: 1498502 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.1475. Min Act: -0.0000

Data Index: 1554815 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.1760. Min Act: -0.0000

Data Index: 1523071 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.2384. Min Act: -0.0000

Data Index: 1254373 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.2440. Min Act: -0.0000

Data Index: 1380155 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.1304. Min Act: -0.0000

Data Index: 1514183 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1496520 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.2328. Min Act: -0.0000

Data Index: 1446596 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0400. Min Act: -0.0000

Data Index: 1605278 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0213. Min Act: -0.0000

Data Index: 1471767 (Python Code)

Max Activating Token Index: 913

Text #15

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0178. Min Act: -0.0000

Data Index: 1453273 (Python Code)

Max Activating Token Index: 82

Text #16

Max Range: 2.4274. Min Range: -2.4274

Max Act: 2.0770. Min Act: -0.0000

Data Index: 1456825 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.8798. Min Act: -0.0000

Data Index: 1652840 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.9607. Min Act: -0.0000

Data Index: 619785 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 2.4274. Min Range: -2.4274

Max Act: 1.9939. Min Act: -0.0000

Data Index: 452072 (C4 (Web Text))

Max Activating Token Index: 625