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

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

Neuron 1532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.7226. Min Act: -0.0002

Data Index: 919497 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6702. Min Act: -0.0002

Data Index: 780277 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6260. Min Act: -0.0002

Data Index: 849069 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6550. Min Act: -0.0001

Data Index: 700052 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6747. Min Act: -0.0001

Data Index: 625189 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5784. Min Act: -0.0001

Data Index: 1486798 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5805. Min Act: -0.0002

Data Index: 1120882 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6073. Min Act: -0.0001

Data Index: 22594 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6180. Min Act: -0.0002

Data Index: 1102417 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5999. Min Act: -0.0001

Data Index: 806938 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5998. Min Act: -0.0001

Data Index: 561939 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6327. Min Act: -0.0001

Data Index: 163014 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6327. Min Act: -0.0001

Data Index: 168434 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6082. Min Act: -0.0001

Data Index: 600697 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1053271 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6277. Min Act: -0.0002

Data Index: 623707 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.6341. Min Act: -0.0002

Data Index: 1347586 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5987. Min Act: -0.0001

Data Index: 543419 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5624. Min Act: -0.0001

Data Index: 922773 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.7226. Min Range: -0.7226

Max Act: 0.5631. Min Act: -0.0001

Data Index: 382972 (C4 (Web Text))

Max Activating Token Index: 793