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

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

Neuron 3575 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: 0.9636. Min Range: -0.9636

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1081925 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9078. Min Act: -0.0002

Data Index: 689638 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9025. Min Act: -0.0002

Data Index: 211758 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9245. Min Act: -0.0001

Data Index: 196803 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8170. Min Act: -0.0001

Data Index: 284987 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8448. Min Act: -0.0001

Data Index: 947701 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8819. Min Act: -0.0001

Data Index: 934174 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8656. Min Act: -0.0001

Data Index: 269479 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8528. Min Act: -0.0002

Data Index: 486370 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8429. Min Act: -0.0001

Data Index: 1267018 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8728. Min Act: -0.0001

Data Index: 498781 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8171. Min Act: -0.0001

Data Index: 527648 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8367. Min Act: -0.0001

Data Index: 314308 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8448. Min Act: -0.0001

Data Index: 325224 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8099. Min Act: -0.0001

Data Index: 812971 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7613. Min Act: -0.0001

Data Index: 930105 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8106. Min Act: -0.0002

Data Index: 901610 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7774. Min Act: -0.0002

Data Index: 1039779 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7958. Min Act: -0.0001

Data Index: 568965 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7704. Min Act: -0.0001

Data Index: 775011 (C4 (Web Text))

Max Activating Token Index: 700