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

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

Neuron 880 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.6329. Min Act: -0.0001

Data Index: 1628441 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4242. Min Act: -0.0001

Data Index: 1610961 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2764. Min Act: -0.0001

Data Index: 1619749 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.5119. Min Act: -0.0001

Data Index: 1495065 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2980. Min Act: -0.0001

Data Index: 1494272 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2924. Min Act: -0.0001

Data Index: 1472535 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2487. Min Act: -0.0001

Data Index: 1493794 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1887. Min Act: -0.0001

Data Index: 1647456 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3071. Min Act: -0.0001

Data Index: 1502315 (Python Code)

Max Activating Token Index: 341

Text #9

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1550. Min Act: -0.0001

Data Index: 1632802 (Python Code)

Max Activating Token Index: 357

Text #10

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2141. Min Act: -0.0001

Data Index: 1376414 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1675. Min Act: -0.0001

Data Index: 1420092 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3537. Min Act: -0.0001

Data Index: 1581098 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2739. Min Act: -0.0001

Data Index: 1620306 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3056. Min Act: -0.0001

Data Index: 1547967 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1640082 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1529466 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2138. Min Act: -0.0001

Data Index: 1483564 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1684. Min Act: -0.0001

Data Index: 1494056 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1413941 (Python Code)

Max Activating Token Index: 294