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

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

Neuron 5323 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: 4.1582. Min Range: -4.1582

Max Act: 4.1582. Min Act: -0.0000

Data Index: 640312 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.9388. Min Act: -0.0000

Data Index: 474508 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.4384. Min Act: -0.0000

Data Index: 251645 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.3503. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.2159. Min Act: -0.0001

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.1977. Min Act: -0.0000

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.4775. Min Act: -0.0000

Data Index: 313429 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.3045. Min Act: -0.0000

Data Index: 143141 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.0272. Min Act: -0.0000

Data Index: 492008 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.8445. Min Act: -0.0000

Data Index: 87511 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.0162. Min Act: -0.0000

Data Index: 857444 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.9919. Min Act: -0.0000

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 4.1582. Min Range: -4.1582

Max Act: 3.1273. Min Act: -0.0000

Data Index: 300586 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.8045. Min Act: -0.0000

Data Index: 1355636 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.9430. Min Act: -0.0001

Data Index: 1325470 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.8235. Min Act: -0.0000

Data Index: 224383 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.8950. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.9071. Min Act: -0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.7586. Min Act: -0.0000

Data Index: 986819 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 4.1582. Min Range: -4.1582

Max Act: 2.7371. Min Act: -0.0000

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 267