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

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

Neuron 4219 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.8366. Min Act: -0.0000

Data Index: 335784 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1042794 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7973. Min Act: -0.0000

Data Index: 723150 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7773. Min Act: 0.0001

Data Index: 1325347 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7483. Min Act: -0.0000

Data Index: 486601 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1330900 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7747. Min Act: -0.0000

Data Index: 757740 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7462. Min Act: -0.0000

Data Index: 773272 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1109591 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7381. Min Act: -0.0000

Data Index: 837883 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6741. Min Act: -0.0000

Data Index: 631284 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7053. Min Act: -0.0000

Data Index: 525711 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6947. Min Act: -0.0000

Data Index: 705374 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1016163 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1154859 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6747. Min Act: -0.0000

Data Index: 615825 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1317409 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6736. Min Act: -0.0000

Data Index: 480423 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6623. Min Act: -0.0000

Data Index: 15239 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1199952 (C4 (Web Text))

Max Activating Token Index: 860