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

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

Neuron 3832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.9253. Min Act: -0.0000

Data Index: 104507 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.5280. Min Act: -0.0000

Data Index: 391450 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.7329. Min Act: -0.0000

Data Index: 508398 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.7157. Min Act: -0.0000

Data Index: 927293 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.6752. Min Act: -0.0000

Data Index: 68489 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.6359. Min Act: -0.0000

Data Index: 494586 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.3683. Min Act: -0.0000

Data Index: 744484 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.3932. Min Act: -0.0000

Data Index: 712966 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.3430. Min Act: -0.0000

Data Index: 555413 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.6023. Min Act: -0.0000

Data Index: 1074063 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.5729. Min Act: -0.0000

Data Index: 991571 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.3379. Min Act: -0.0000

Data Index: 692668 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.5821. Min Act: -0.0000

Data Index: 365961 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.7036. Min Act: -0.0000

Data Index: 337679 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.5694. Min Act: -0.0000

Data Index: 254946 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.4203. Min Act: -0.0000

Data Index: 90935 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.2991. Min Act: -0.0000

Data Index: 371249 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.5306. Min Act: -0.0000

Data Index: 525603 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.3950. Min Act: -0.0000

Data Index: 701417 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 2.9253. Min Range: -2.9253

Max Act: 2.4874. Min Act: -0.0000

Data Index: 221303 (C4 (Web Text))

Max Activating Token Index: 970