Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4317 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.6180. Min Act: -0.0000

Data Index: 715763 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1243864 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4332. Min Act: -0.0000

Data Index: 288364 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1079720 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4253. Min Act: -0.0000

Data Index: 495818 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1217249 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1039429 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3981. Min Act: -0.0000

Data Index: 623722 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3821. Min Act: -0.0000

Data Index: 840852 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3863. Min Act: -0.0000

Data Index: 836105 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1250297 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1070959 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3911. Min Act: -0.0000

Data Index: 983236 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3686. Min Act: -0.0000

Data Index: 721884 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1196979 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1218484 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1295808 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3405. Min Act: -0.0000

Data Index: 157758 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1096466 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3285. Min Act: -0.0000

Data Index: 340532 (C4 (Web Text))

Max Activating Token Index: 757