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

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

Neuron 641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3414. Min Act: -0.0000

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3424. Min Act: -0.0000

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3478. Min Act: -0.0000

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3503. Min Act: -0.0000

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3251. Min Act: -0.0000

Data Index: 716035 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3213. Min Act: -0.0000

Data Index: 605802 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3299. Min Act: -0.0000

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3131. Min Act: -0.0000

Data Index: 439642 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3038. Min Act: -0.0000

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3021. Min Act: -0.0000

Data Index: 639717 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3207. Min Act: -0.0000

Data Index: 840542 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2990. Min Act: -0.0000

Data Index: 795714 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3153. Min Act: -0.0000

Data Index: 319693 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3174. Min Act: -0.0000

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2980. Min Act: -0.0000

Data Index: 970328 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3090. Min Act: -0.0000

Data Index: 581236 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3046. Min Act: -0.0000

Data Index: 700836 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2751. Min Act: -0.0000

Data Index: 325381 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 877