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

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

Neuron 340 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1572138 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1422411 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1371129 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1364609 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1476286 (Python Code)

Max Activating Token Index: 804

Text #5

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1574643 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1236116 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1401227 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1880. Min Act: -0.0000

Data Index: 844536 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0691. Min Act: -0.0000

Data Index: 104044 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1376707 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1614638 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1394834 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1576993 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1585314 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1380773 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0587. Min Act: -0.0000

Data Index: 453671 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1564877 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1475301 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 1.4277. Min Range: -1.4277

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1406356 (Python Code)

Max Activating Token Index: 195