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

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

Neuron 2296 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: 2.5317. Min Range: -2.5317

Max Act: 2.4286. Min Act: -0.0000

Data Index: 187028 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 2.5317. Min Range: -2.5317

Max Act: 2.5317. Min Act: -0.0000

Data Index: 499487 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 2.5317. Min Range: -2.5317

Max Act: 2.3094. Min Act: -0.0000

Data Index: 203801 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 2.5317. Min Range: -2.5317

Max Act: 2.0134. Min Act: -0.0000

Data Index: 1503708 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.9772. Min Act: -0.0000

Data Index: 313120 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.7788. Min Act: 0.0000

Data Index: 1232590 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.8603. Min Act: -0.0000

Data Index: 461381 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.8379. Min Act: -0.0000

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.7369. Min Act: -0.0000

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1128852 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.6687. Min Act: -0.0000

Data Index: 1199199 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.6535. Min Act: -0.0000

Data Index: 418050 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5311. Min Act: -0.0000

Data Index: 562007 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.8118. Min Act: -0.0000

Data Index: 695491 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.6080. Min Act: -0.0000

Data Index: 276169 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5887. Min Act: -0.0000

Data Index: 838602 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5961. Min Act: 0.0000

Data Index: 1325941 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5752. Min Act: -0.0000

Data Index: 848729 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5424. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 2.5317. Min Range: -2.5317

Max Act: 1.5623. Min Act: -0.0000

Data Index: 600026 (C4 (Web Text))

Max Activating Token Index: 589