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

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

Neuron 2040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3770. Min Range: -3.3770

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1461048 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 3.3770. Min Range: -3.3770

Max Act: 3.1181. Min Act: -0.0000

Data Index: 1493853 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 3.3770. Min Range: -3.3770

Max Act: 3.2266. Min Act: -0.0000

Data Index: 1474331 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.8599. Min Act: -0.0000

Data Index: 1493839 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.9538. Min Act: -0.0000

Data Index: 1477218 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.9587. Min Act: -0.0000

Data Index: 1448606 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 3.3770. Min Range: -3.3770

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1652774 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5022. Min Act: -0.0000

Data Index: 1624258 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5539. Min Act: -0.0000

Data Index: 1623479 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.7835. Min Act: -0.0000

Data Index: 1614993 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.7293. Min Act: -0.0000

Data Index: 1369411 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5940. Min Act: -0.0000

Data Index: 1543284 (Python Code)

Max Activating Token Index: 603

Text #12

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5894. Min Act: -0.0000

Data Index: 1499725 (Python Code)

Max Activating Token Index: 810

Text #13

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1551217 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.2927. Min Act: -0.0000

Data Index: 1509141 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.5350. Min Act: -0.0000

Data Index: 1393040 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.6247. Min Act: -0.0000

Data Index: 1388984 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1486248 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1605918 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 3.3770. Min Range: -3.3770

Max Act: 2.6801. Min Act: -0.0000

Data Index: 1459677 (Python Code)

Max Activating Token Index: 650