Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 63 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1233757 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1028660 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1105547 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1566. Min Act: -0.0001

Data Index: 470705 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1569. Min Act: -0.0000

Data Index: 802301 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1302188 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1517. Min Act: -0.0001

Data Index: 260635 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1466. Min Act: -0.0001

Data Index: 46251 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1435. Min Act: -0.0001

Data Index: 263668 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1344. Min Act: -0.0000

Data Index: 481592 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1382. Min Act: -0.0001

Data Index: 983407 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1480. Min Act: -0.0001

Data Index: 678205 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1389. Min Act: -0.0001

Data Index: 728758 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1340. Min Act: -0.0000

Data Index: 485292 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1140797 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1322. Min Act: -0.0001

Data Index: 896182 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1041461 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1276. Min Act: -0.0001

Data Index: 957817 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1323890 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1246. Min Act: -0.0001

Data Index: 263529 (C4 (Web Text))

Max Activating Token Index: 948