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

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

Neuron 4310 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.6100. Min Act: -0.0001

Data Index: 265579 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.4973. Min Act: -0.0001

Data Index: 1133318 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.4639. Min Act: -0.0001

Data Index: 898366 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.3633. Min Act: -0.0001

Data Index: 632990 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.2567. Min Act: -0.0001

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.1721. Min Act: -0.0001

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.2136. Min Act: -0.0001

Data Index: 608814 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.2604. Min Act: -0.0001

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.1078. Min Act: -0.0001

Data Index: 399796 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.2022. Min Act: -0.0001

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.1044. Min Act: -0.0001

Data Index: 28376 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0336. Min Act: -0.0001

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1051194 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0724. Min Act: -0.0001

Data Index: 190482 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0380. Min Act: -0.0001

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1129636 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.1427. Min Act: -0.0001

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0451. Min Act: -0.0001

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.1025. Min Act: -0.0001

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.6100. Min Range: -1.6100

Max Act: 1.0105. Min Act: -0.0001

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 165