Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3799 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.9754. Min Act: -0.0000

Data Index: 1093862 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.0138. Min Range: -3.0138

Max Act: 3.0138. Min Act: -0.0000

Data Index: 1060073 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.4651. Min Act: -0.0000

Data Index: 1398895 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.6353. Min Act: -0.0000

Data Index: 852056 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.6213. Min Act: -0.0000

Data Index: 603789 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.4508. Min Act: -0.0000

Data Index: 1443204 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1536422 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.2607. Min Act: -0.0000

Data Index: 1426382 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.4520. Min Act: -0.0000

Data Index: 1394297 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.4940. Min Act: -0.0000

Data Index: 1059404 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.3302. Min Act: -0.0000

Data Index: 1492225 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.2777. Min Act: -0.0000

Data Index: 1161943 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1571918 (Python Code)

Max Activating Token Index: 421

Text #13

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.1464. Min Act: -0.0000

Data Index: 1194108 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.2456. Min Act: -0.0000

Data Index: 1479087 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.1121. Min Act: -0.0000

Data Index: 971700 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.0833. Min Act: -0.0000

Data Index: 80561 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1487575 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.1750. Min Act: -0.0000

Data Index: 1566598 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 3.0138. Min Range: -3.0138

Max Act: 2.1811. Min Act: -0.0000

Data Index: 820396 (C4 (Web Text))

Max Activating Token Index: 642