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

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

Neuron 1393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3532. Min Act: -0.0000

Data Index: 289500 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2937. Min Act: -0.0001

Data Index: 644367 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2579. Min Act: -0.0000

Data Index: 637762 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2427. Min Act: -0.0000

Data Index: 753518 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2433. Min Act: -0.0001

Data Index: 43397 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1154057 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1185636 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2228. Min Act: -0.0000

Data Index: 893538 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2123. Min Act: -0.0000

Data Index: 600129 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2194. Min Act: -0.0000

Data Index: 85504 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2084. Min Act: -0.0001

Data Index: 605767 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2111. Min Act: -0.0000

Data Index: 22671 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1349713 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2144. Min Act: -0.0000

Data Index: 862304 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1283892 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1921. Min Act: -0.0000

Data Index: 298422 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1976. Min Act: -0.0000

Data Index: 744281 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2017. Min Act: -0.0000

Data Index: 549189 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1108347 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.1838. Min Act: -0.0001

Data Index: 833201 (C4 (Web Text))

Max Activating Token Index: 241