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

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

Neuron 3630 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: 1.4732. Min Range: -1.4732

Max Act: 1.4732. Min Act: -0.0000

Data Index: 537419 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.4732. Min Range: -1.4732

Max Act: 1.0440. Min Act: -0.0000

Data Index: 630617 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.9906. Min Act: 0.0001

Data Index: 990410 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.9078. Min Act: -0.0000

Data Index: 140759 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.9404. Min Act: -0.0000

Data Index: 179949 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.7743. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.7792. Min Act: -0.0000

Data Index: 223419 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.7545. Min Act: -0.0000

Data Index: 442342 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.7349. Min Act: -0.0000

Data Index: 893878 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1187567 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6774. Min Act: -0.0000

Data Index: 426624 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6886. Min Act: -0.0000

Data Index: 243397 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1153469 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6864. Min Act: -0.0000

Data Index: 892637 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1223137 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6694. Min Act: -0.0000

Data Index: 231596 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6509. Min Act: -0.0000

Data Index: 182103 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6381. Min Act: -0.0000

Data Index: 171140 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.4732. Min Range: -1.4732

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1241581 (C4 (Web Text))

Max Activating Token Index: 907