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

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

Neuron 5736 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1990. Min Range: -1.1990

Max Act: 1.1990. Min Act: -0.0000

Data Index: 397246 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.7563. Min Act: -0.0000

Data Index: 819614 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5964. Min Act: -0.0000

Data Index: 579834 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1019972 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.6195. Min Act: -0.0000

Data Index: 652484 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5842. Min Act: -0.0000

Data Index: 729899 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.6070. Min Act: -0.0000

Data Index: 145614 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5743. Min Act: -0.0000

Data Index: 585766 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1140234 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1068163 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5497. Min Act: -0.0000

Data Index: 847221 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1061525 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5665. Min Act: -0.0000

Data Index: 226014 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5016. Min Act: -0.0000

Data Index: 159977 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.5001. Min Act: -0.0000

Data Index: 945439 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1340708 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1230115 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.4708. Min Act: -0.0000

Data Index: 537036 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1244534 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.1990. Min Range: -1.1990

Max Act: 0.4492. Min Act: -0.0000

Data Index: 565681 (C4 (Web Text))

Max Activating Token Index: 971