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

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

Neuron 3603 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.2640. Min Act: -0.0001

Data Index: 65654 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.1632. Min Act: -0.0001

Data Index: 1104979 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.2640. Min Range: -1.2640

Max Act: 1.0138. Min Act: -0.0001

Data Index: 145208 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9165. Min Act: -0.0001

Data Index: 404053 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9426. Min Act: -0.0001

Data Index: 1064593 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8808. Min Act: -0.0001

Data Index: 1242524 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.9513. Min Act: -0.0001

Data Index: 956433 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7744. Min Act: -0.0001

Data Index: 991202 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8841. Min Act: -0.0001

Data Index: 185450 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8340. Min Act: -0.0001

Data Index: 535125 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8218. Min Act: -0.0001

Data Index: 209069 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8184. Min Act: -0.0001

Data Index: 802138 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7933. Min Act: -0.0001

Data Index: 1081200 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8089. Min Act: -0.0001

Data Index: 1319322 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8595. Min Act: -0.0001

Data Index: 264025 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7647. Min Act: -0.0001

Data Index: 582961 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8075. Min Act: -0.0001

Data Index: 613413 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7991. Min Act: -0.0001

Data Index: 545954 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.8184. Min Act: -0.0001

Data Index: 659581 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.2640. Min Range: -1.2640

Max Act: 0.7619. Min Act: -0.0001

Data Index: 1132867 (C4 (Web Text))

Max Activating Token Index: 336