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

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

Neuron 296 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4173. Min Act: -0.0000

Data Index: 847543 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1303474 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1317731 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.4350. Min Act: -0.0000

Data Index: 558901 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3716. Min Act: -0.0000

Data Index: 267776 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3576. Min Act: -0.0000

Data Index: 281819 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1254115 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3229. Min Act: -0.0000

Data Index: 605005 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1555834 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1459144 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3301. Min Act: -0.0000

Data Index: 561664 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1616802 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3154. Min Act: -0.0000

Data Index: 926822 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1376944 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1095206 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3298. Min Act: -0.0000

Data Index: 612909 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3310. Min Act: -0.0000

Data Index: 987913 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1228564 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3158. Min Act: -0.0000

Data Index: 232695 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.4589. Min Range: -0.4589

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1366933 (Python Code)

Max Activating Token Index: 281