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

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

Neuron 1770 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1214966 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6716. Min Act: -0.0001

Data Index: 338759 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6409. Min Act: -0.0001

Data Index: 892619 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6226. Min Act: -0.0001

Data Index: 696113 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6332. Min Act: -0.0001

Data Index: 875146 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1346256 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6321. Min Act: -0.0001

Data Index: 819248 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6281. Min Act: -0.0001

Data Index: 419516 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6182. Min Act: -0.0001

Data Index: 655272 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6270. Min Act: -0.0001

Data Index: 328083 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1221323 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6040. Min Act: -0.0001

Data Index: 149014 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5941. Min Act: -0.0001

Data Index: 929951 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1184367 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1089962 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5766. Min Act: -0.0001

Data Index: 1119764 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5802. Min Act: -0.0001

Data Index: 635049 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5830. Min Act: -0.0001

Data Index: 1325425 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5948. Min Act: -0.0001

Data Index: 761429 (C4 (Web Text))

Max Activating Token Index: 264