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

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

Neuron 2725 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: 0.4485. Min Range: -0.4485

Max Act: 0.4485. Min Act: -0.0000

Data Index: 821797 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4214. Min Act: -0.0000

Data Index: 786552 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1262855 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1190297 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3902. Min Act: -0.0000

Data Index: 608766 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3779. Min Act: -0.0000

Data Index: 819281 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1531837 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1333384 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3741. Min Act: -0.0000

Data Index: 58501 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3507. Min Act: -0.0000

Data Index: 58175 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1163464 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1524106 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1608304 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1373502 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1601316 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3279. Min Act: -0.0000

Data Index: 18158 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3332. Min Act: -0.0000

Data Index: 223121 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3215. Min Act: -0.0000

Data Index: 395841 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3450. Min Act: -0.0000

Data Index: 483480 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1419240 (Python Code)

Max Activating Token Index: 753