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

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

Neuron 3113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.9957. Min Act: -0.0001

Data Index: 391729 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1280083 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.9997. Min Act: -0.0001

Data Index: 544440 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.9247. Min Act: -0.0001

Data Index: 754571 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1337208 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8274. Min Act: -0.0001

Data Index: 109281 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8369. Min Act: -0.0001

Data Index: 991529 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1139206 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7660. Min Act: -0.0001

Data Index: 368635 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8899. Min Act: -0.0001

Data Index: 69777 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7331. Min Act: -0.0001

Data Index: 1222822 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7292. Min Act: -0.0001

Data Index: 954614 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1306665 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7967. Min Act: -0.0001

Data Index: 625934 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1124304 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7972. Min Act: -0.0001

Data Index: 159230 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7688. Min Act: -0.0001

Data Index: 940641 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8213. Min Act: -0.0001

Data Index: 184591 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.7108. Min Act: -0.0001

Data Index: 1292977 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.9997. Min Range: -0.9997

Max Act: 0.8066. Min Act: -0.0001

Data Index: 228424 (C4 (Web Text))

Max Activating Token Index: 566