Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3094 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3970. Min Act: -0.0001

Data Index: 970749 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3315. Min Act: -0.0000

Data Index: 41584 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3153. Min Act: -0.0000

Data Index: 5419 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3235. Min Act: -0.0001

Data Index: 518277 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3141. Min Act: -0.0001

Data Index: 181457 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1195175 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2815. Min Act: -0.0001

Data Index: 1281140 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1049525 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1327749 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2750. Min Act: -0.0001

Data Index: 366344 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2739. Min Act: -0.0000

Data Index: 443067 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2552. Min Act: -0.0001

Data Index: 467338 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2712. Min Act: -0.0001

Data Index: 501750 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2694. Min Act: -0.0001

Data Index: 891435 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2854. Min Act: -0.0001

Data Index: 887293 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1480438 (Python Code)

Max Activating Token Index: 657

Text #16

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2732. Min Act: -0.0001

Data Index: 890533 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2402. Min Act: -0.0000

Data Index: 41200 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2558. Min Act: -0.0001

Data Index: 596601 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2642. Min Act: -0.0001

Data Index: 699168 (C4 (Web Text))

Max Activating Token Index: 993