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

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

Neuron 1582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.6462. Min Act: -0.0000

Data Index: 635402 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.2784. Min Act: -0.0000

Data Index: 802433 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.5177. Min Act: -0.0000

Data Index: 1276199 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.0656. Min Act: -0.0000

Data Index: 1017145 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.8980. Min Act: -0.0000

Data Index: 96636 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.1745. Min Act: -0.0000

Data Index: 1042722 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.2547. Min Act: -0.0000

Data Index: 226931 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.0650. Min Act: -0.0000

Data Index: 1215497 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.7960. Min Act: -0.0000

Data Index: 938870 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.1982. Min Act: -0.0000

Data Index: 380234 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.9946. Min Act: -0.0000

Data Index: 923938 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.8157. Min Act: -0.0000

Data Index: 141150 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.6462. Min Range: -3.6462

Max Act: 3.1322. Min Act: -0.0000

Data Index: 1239953 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.8697. Min Act: -0.0000

Data Index: 369143 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1114402 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.9250. Min Act: -0.0000

Data Index: 855880 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.6816. Min Act: -0.0000

Data Index: 945696 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1096765 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.4977. Min Act: -0.0000

Data Index: 344224 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 3.6462. Min Range: -3.6462

Max Act: 2.6409. Min Act: -0.0000

Data Index: 783398 (C4 (Web Text))

Max Activating Token Index: 40