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

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

Neuron 5430 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.4046. Min Act: -0.0001

Data Index: 43895 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.9943. Min Act: -0.0000

Data Index: 1358652 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.7479. Min Act: -0.0001

Data Index: 304828 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.4100. Min Act: -0.0001

Data Index: 425170 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.5682. Min Act: -0.0001

Data Index: 413325 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 4.9943. Min Range: -4.9943

Max Act: 3.8950. Min Act: -0.0001

Data Index: 370940 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.6507. Min Act: -0.0000

Data Index: 252335 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.4271. Min Act: -0.0000

Data Index: 201798 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 4.9943. Min Range: -4.9943

Max Act: 3.7433. Min Act: -0.0000

Data Index: 1082544 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.3414. Min Act: -0.0000

Data Index: 598567 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.1756. Min Act: -0.0001

Data Index: 135099 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.1944. Min Act: -0.0000

Data Index: 610093 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 4.9943. Min Range: -4.9943

Max Act: 3.9756. Min Act: -0.0000

Data Index: 404645 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 4.9943. Min Range: -4.9943

Max Act: 3.8031. Min Act: -0.0001

Data Index: 1319430 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 4.9943. Min Range: -4.9943

Max Act: 3.8092. Min Act: -0.0001

Data Index: 926676 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.3831. Min Act: -0.0000

Data Index: 521347 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.1527. Min Act: -0.0001

Data Index: 128720 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.0020. Min Act: -0.0001

Data Index: 821274 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.0996. Min Act: -0.0000

Data Index: 1203223 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 4.9943. Min Range: -4.9943

Max Act: 4.0575. Min Act: -0.0001

Data Index: 991002 (C4 (Web Text))

Max Activating Token Index: 18