Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.2937. Min Act: -0.0000

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.0855. Min Act: -0.0000

Data Index: 465164 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 4.2937. Min Range: -4.2937

Max Act: 4.0273. Min Act: -0.0000

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.6484. Min Act: -0.0000

Data Index: 244707 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.6573. Min Act: -0.0000

Data Index: 932651 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.4759. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.6310. Min Act: -0.0000

Data Index: 1341520 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.5264. Min Act: -0.0000

Data Index: 1273727 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.2977. Min Act: -0.0000

Data Index: 492253 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.5764. Min Act: -0.0000

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.2938. Min Act: -0.0000

Data Index: 1161573 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.3729. Min Act: -0.0000

Data Index: 807208 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.3444. Min Act: -0.0000

Data Index: 1039101 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.3409. Min Act: -0.0000

Data Index: 11458 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 4.2937. Min Range: -4.2937

Max Act: 2.9856. Min Act: -0.0000

Data Index: 1214949 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.3297. Min Act: -0.0000

Data Index: 618359 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.3006. Min Act: -0.0000

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.1865. Min Act: -0.0000

Data Index: 1247528 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.2826. Min Act: -0.0000

Data Index: 821519 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 4.2937. Min Range: -4.2937

Max Act: 3.2147. Min Act: -0.0000

Data Index: 258317 (C4 (Web Text))

Max Activating Token Index: 562