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

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

Neuron 2385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4752. Min Act: -0.0001

Data Index: 36114 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4884. Min Act: -0.0001

Data Index: 362314 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4925. Min Act: -0.0001

Data Index: 15437 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4919. Min Act: -0.0001

Data Index: 1080836 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4816. Min Act: -0.0001

Data Index: 358003 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1156320 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4691. Min Act: -0.0001

Data Index: 771576 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4657. Min Act: -0.0001

Data Index: 685519 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.5061. Min Act: -0.0001

Data Index: 978458 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4374. Min Act: -0.0001

Data Index: 220986 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4106. Min Act: -0.0001

Data Index: 157281 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4316. Min Act: -0.0001

Data Index: 744039 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4582. Min Act: -0.0001

Data Index: 219616 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4020. Min Act: -0.0001

Data Index: 275811 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4530. Min Act: -0.0001

Data Index: 695128 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4351. Min Act: -0.0001

Data Index: 1608332 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4313. Min Act: -0.0001

Data Index: 733621 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4174. Min Act: -0.0001

Data Index: 765624 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1109424 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4413. Min Act: -0.0001

Data Index: 1586041 (Python Code)

Max Activating Token Index: 123