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

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

Neuron 2809 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: 0.3416. Min Range: -0.3416

Max Act: 0.3416. Min Act: 0.0000

Data Index: 550761 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.3325. Min Act: -0.0000

Data Index: 873751 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1308684 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2863. Min Act: -0.0000

Data Index: 6725 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1163466 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2493. Min Act: -0.0000

Data Index: 674124 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2462. Min Act: -0.0000

Data Index: 780341 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2437. Min Act: 0.0000

Data Index: 1095066 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1301019 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2485. Min Act: -0.0000

Data Index: 986338 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2348. Min Act: -0.0000

Data Index: 240358 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2337. Min Act: 0.0000

Data Index: 839321 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1327683 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1275082 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1299014 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2286. Min Act: -0.0000

Data Index: 76004 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2301. Min Act: 0.0000

Data Index: 999639 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2129. Min Act: -0.0000

Data Index: 317844 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2209. Min Act: 0.0000

Data Index: 196328 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2153. Min Act: -0.0000

Data Index: 41277 (C4 (Web Text))

Max Activating Token Index: 822