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

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

Neuron 1570 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: 0.6456. Min Range: -0.6456

Max Act: 0.6456. Min Act: -0.0001

Data Index: 270898 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4967. Min Act: -0.0001

Data Index: 292243 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5020. Min Act: -0.0001

Data Index: 331051 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4806. Min Act: -0.0001

Data Index: 1289397 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4781. Min Act: -0.0001

Data Index: 57277 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1185641 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1542609 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1169327 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1293490 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1621400 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1654440 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3460. Min Act: -0.0001

Data Index: 984365 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1350499 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3547. Min Act: -0.0001

Data Index: 572498 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3332. Min Act: -0.0001

Data Index: 497397 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1490336 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1611502 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3399. Min Act: -0.0001

Data Index: 974208 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1117446 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.3269. Min Act: -0.0001

Data Index: 454850 (C4 (Web Text))

Max Activating Token Index: 395