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

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

Neuron 4821 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: 1.8043. Min Range: -1.8043

Max Act: 1.7945. Min Act: -0.0001

Data Index: 1576476 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.8043. Min Act: -0.0001

Data Index: 1493428 (Python Code)

Max Activating Token Index: 370

Text #2

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.6536. Min Act: -0.0001

Data Index: 1649062 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.6253. Min Act: -0.0001

Data Index: 506670 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.5056. Min Act: -0.0001

Data Index: 962919 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4370. Min Act: -0.0001

Data Index: 890535 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.5043. Min Act: -0.0001

Data Index: 58599 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4211. Min Act: -0.0001

Data Index: 1120953 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4460. Min Act: -0.0001

Data Index: 294193 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.3623. Min Act: -0.0001

Data Index: 117023 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4201. Min Act: -0.0001

Data Index: 178803 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4553. Min Act: -0.0001

Data Index: 1223861 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.3161. Min Act: -0.0001

Data Index: 679246 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4728. Min Act: -0.0001

Data Index: 791670 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.3990. Min Act: -0.0001

Data Index: 914505 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.3839. Min Act: -0.0001

Data Index: 506373 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4314. Min Act: -0.0001

Data Index: 1022853 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4414. Min Act: -0.0001

Data Index: 153416 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.2652. Min Act: -0.0001

Data Index: 1214572 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.2827. Min Act: -0.0001

Data Index: 621775 (C4 (Web Text))

Max Activating Token Index: 402