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

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

Neuron 2833 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.3806. Min Act: -0.0001

Data Index: 1140306 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.2602. Min Act: -0.0001

Data Index: 246370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.2730. Min Act: -0.0001

Data Index: 1510 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.2078. Min Act: -0.0001

Data Index: 554468 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.1261. Min Act: -0.0001

Data Index: 789390 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0811. Min Act: -0.0001

Data Index: 92042 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1021769 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.1180. Min Act: -0.0001

Data Index: 633985 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.1087. Min Act: -0.0001

Data Index: 246088 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0659. Min Act: -0.0001

Data Index: 109337 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0465. Min Act: -0.0001

Data Index: 841310 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0413. Min Act: -0.0001

Data Index: 996184 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0381. Min Act: -0.0001

Data Index: 279347 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.3806. Min Range: -1.3806

Max Act: 0.9585. Min Act: -0.0001

Data Index: 426705 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0679. Min Act: -0.0001

Data Index: 191024 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0299. Min Act: -0.0001

Data Index: 684865 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0636. Min Act: -0.0001

Data Index: 1110683 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0209. Min Act: -0.0001

Data Index: 308934 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0552. Min Act: -0.0001

Data Index: 228347 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.3806. Min Range: -1.3806

Max Act: 1.0582. Min Act: -0.0001

Data Index: 660058 (C4 (Web Text))

Max Activating Token Index: 494