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

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

Neuron 1166 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.7276. Min Act: 0.0000

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.3040. Min Act: 0.0000

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.2046. Min Act: 0.0000

Data Index: 1349757 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.2213. Min Act: -0.0000

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.2369. Min Act: 0.0000

Data Index: 766141 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.1574. Min Act: -0.0000

Data Index: 664420 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.1546. Min Act: 0.0000

Data Index: 1004379 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1163816 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.2128. Min Act: -0.0000

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9757. Min Act: 0.0000

Data Index: 61699 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.3348. Min Act: -0.0000

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.7276. Min Range: -1.7276

Max Act: 1.0400. Min Act: -0.0000

Data Index: 39723 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9607. Min Act: 0.0001

Data Index: 1500861 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9250. Min Act: 0.0000

Data Index: 1480168 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9686. Min Act: 0.0000

Data Index: 1520468 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.8819. Min Act: 0.0000

Data Index: 872353 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9144. Min Act: 0.0000

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1426346 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.7276. Min Range: -1.7276

Max Act: 0.9151. Min Act: 0.0000

Data Index: 1378960 (Python Code)

Max Activating Token Index: 71