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

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

Neuron 1997 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1399688 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.8551. Min Act: -0.0000

Data Index: 511204 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7775. Min Act: -0.0000

Data Index: 599295 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1100266 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7626. Min Act: -0.0000

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1122651 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1172248 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6859. Min Act: -0.0000

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6796. Min Act: -0.0000

Data Index: 655121 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6522. Min Act: -0.0000

Data Index: 672272 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5904. Min Act: -0.0000

Data Index: 10841 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1393543 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1301823 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5454. Min Act: -0.0000

Data Index: 293020 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5467. Min Act: -0.0000

Data Index: 959047 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5448. Min Act: -0.0000

Data Index: 191488 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5319. Min Act: -0.0000

Data Index: 798977 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5804. Min Act: -0.0000

Data Index: 542317 (C4 (Web Text))

Max Activating Token Index: 593