Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2759 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.5350. Min Act: -0.0003

Data Index: 1330191 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4362. Min Act: -0.0003

Data Index: 1057990 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.5443. Min Act: -0.0003

Data Index: 1057228 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4170. Min Act: -0.0003

Data Index: 824163 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.3668. Min Act: -0.0003

Data Index: 976283 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4320. Min Act: -0.0003

Data Index: 846222 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.3092. Min Act: -0.0003

Data Index: 68322 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.3047. Min Act: -0.0003

Data Index: 588809 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.3547. Min Act: -0.0003

Data Index: 627167 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.3457. Min Act: -0.0003

Data Index: 687824 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2530. Min Act: -0.0003

Data Index: 890686 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2035. Min Act: -0.0003

Data Index: 144165 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2022. Min Act: -0.0003

Data Index: 350129 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2397. Min Act: -0.0003

Data Index: 1216297 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1018. Min Act: -0.0003

Data Index: 1250494 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1241. Min Act: -0.0003

Data Index: 992467 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2184. Min Act: -0.0003

Data Index: 80033 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2153. Min Act: -0.0003

Data Index: 49447 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1772. Min Act: -0.0003

Data Index: 839618 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2003. Min Act: -0.0003

Data Index: 1084423 (C4 (Web Text))

Max Activating Token Index: 829