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

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

Neuron 1809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2457. Min Range: -1.2457

Max Act: 1.2457. Min Act: -0.0001

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.2457. Min Range: -1.2457

Max Act: 1.0292. Min Act: -0.0001

Data Index: 726407 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9723. Min Act: -0.0001

Data Index: 56873 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9745. Min Act: -0.0001

Data Index: 28647 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9964. Min Act: -0.0001

Data Index: 1122189 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.2457. Min Range: -1.2457

Max Act: 1.0236. Min Act: -0.0001

Data Index: 574681 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9857. Min Act: -0.0001

Data Index: 657570 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.8960. Min Act: -0.0001

Data Index: 1153490 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9793. Min Act: -0.0001

Data Index: 815555 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9508. Min Act: -0.0001

Data Index: 213394 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.8945. Min Act: -0.0001

Data Index: 794410 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9436. Min Act: -0.0001

Data Index: 1138555 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9386. Min Act: -0.0001

Data Index: 130603 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1261184 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9433. Min Act: -0.0001

Data Index: 668391 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9334. Min Act: -0.0001

Data Index: 335513 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9208. Min Act: -0.0001

Data Index: 900026 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9290. Min Act: -0.0001

Data Index: 880611 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9122. Min Act: -0.0001

Data Index: 533815 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.2457. Min Range: -1.2457

Max Act: 0.9098. Min Act: -0.0001

Data Index: 335262 (C4 (Web Text))

Max Activating Token Index: 430