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

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

Neuron 3017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.2047. Min Act: -0.0001

Data Index: 837235 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.8807. Min Act: -0.0001

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.1550. Min Act: -0.0001

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.2047. Min Range: -3.2047

Max Act: 3.0039. Min Act: -0.0001

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.9432. Min Act: -0.0001

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.9041. Min Act: -0.0001

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.8746. Min Act: -0.0001

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.7064. Min Act: -0.0001

Data Index: 47504 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4474. Min Act: -0.0001

Data Index: 1010808 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.6658. Min Act: -0.0001

Data Index: 265897 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4572. Min Act: -0.0001

Data Index: 434516 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4336. Min Act: -0.0001

Data Index: 924166 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.2852. Min Act: -0.0001

Data Index: 1269121 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.2547. Min Act: -0.0001

Data Index: 526159 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.2563. Min Act: -0.0001

Data Index: 954550 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.3710. Min Act: -0.0001

Data Index: 277321 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4313. Min Act: -0.0001

Data Index: 952241 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.2155. Min Act: -0.0001

Data Index: 353025 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.4312. Min Act: -0.0001

Data Index: 128823 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 3.2047. Min Range: -3.2047

Max Act: 2.3005. Min Act: -0.0001

Data Index: 169221 (C4 (Web Text))

Max Activating Token Index: 503