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

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

Neuron 1261 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6862. Min Act: -0.0004

Data Index: 1025701 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6732. Min Act: -0.0004

Data Index: 760421 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6150. Min Act: -0.0004

Data Index: 248830 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6299. Min Act: -0.0004

Data Index: 598582 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5784. Min Act: -0.0004

Data Index: 297492 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6463. Min Act: -0.0004

Data Index: 601186 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6165. Min Act: -0.0004

Data Index: 1173082 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5994. Min Act: -0.0004

Data Index: 1085425 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5608. Min Act: -0.0004

Data Index: 167487 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5951. Min Act: -0.0004

Data Index: 550159 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.6063. Min Act: -0.0004

Data Index: 1228709 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5663. Min Act: -0.0004

Data Index: 744371 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5786. Min Act: -0.0004

Data Index: 382621 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5599. Min Act: -0.0004

Data Index: 399827 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5754. Min Act: -0.0004

Data Index: 84339 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5714. Min Act: -0.0004

Data Index: 904542 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5509. Min Act: -0.0004

Data Index: 282985 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5455. Min Act: -0.0004

Data Index: 458544 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5616. Min Act: -0.0004

Data Index: 957412 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.6862. Min Range: -0.6862

Max Act: 0.5049. Min Act: -0.0004

Data Index: 1303668 (C4 (Web Text))

Max Activating Token Index: 920