Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4018. Min Act: -0.0001

Data Index: 892340 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4181. Min Act: -0.0001

Data Index: 270267 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3955. Min Act: -0.0001

Data Index: 631404 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4067. Min Act: -0.0001

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4186. Min Act: -0.0001

Data Index: 762849 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4125. Min Act: -0.0001

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3879. Min Act: -0.0001

Data Index: 407585 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3813. Min Act: -0.0001

Data Index: 865823 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3745. Min Act: -0.0001

Data Index: 676888 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3801. Min Act: -0.0001

Data Index: 343687 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3918. Min Act: -0.0001

Data Index: 833421 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3572. Min Act: -0.0001

Data Index: 1119924 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4296. Min Act: -0.0001

Data Index: 608634 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1054070 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4124. Min Act: -0.0001

Data Index: 178263 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3716. Min Act: -0.0001

Data Index: 641831 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3450. Min Act: -0.0001

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1325108 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3950. Min Act: -0.0001

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3683. Min Act: -0.0001

Data Index: 158513 (C4 (Web Text))

Max Activating Token Index: 721