Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2296 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8841. Min Act: -0.0003

Data Index: 789669 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8227. Min Act: -0.0003

Data Index: 644274 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8368. Min Act: -0.0003

Data Index: 558701 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8540. Min Act: -0.0003

Data Index: 1077516 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8728. Min Act: -0.0003

Data Index: 48460 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8094. Min Act: -0.0003

Data Index: 1224280 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8079. Min Act: -0.0003

Data Index: 1061045 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8481. Min Act: -0.0003

Data Index: 1232147 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8323. Min Act: -0.0003

Data Index: 498619 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8113. Min Act: -0.0003

Data Index: 542978 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7722. Min Act: -0.0003

Data Index: 323216 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7652. Min Act: -0.0003

Data Index: 971834 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9532. Min Act: -0.0003

Data Index: 797047 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7755. Min Act: -0.0003

Data Index: 119832 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7712. Min Act: -0.0003

Data Index: 1030516 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7514. Min Act: -0.0003

Data Index: 579864 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7266. Min Act: -0.0003

Data Index: 165737 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7411. Min Act: -0.0003

Data Index: 600954 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7641. Min Act: -0.0003

Data Index: 896459 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.7406. Min Act: -0.0003

Data Index: 945697 (C4 (Web Text))

Max Activating Token Index: 737