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

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

Neuron 3922 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: 0.8474. Min Range: -0.8474

Max Act: 0.8311. Min Act: -0.0000

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8474. Min Act: -0.0000

Data Index: 334741 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1261246 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1150258 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7025. Min Act: -0.0000

Data Index: 143915 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6215. Min Act: -0.0000

Data Index: 215634 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5921. Min Act: -0.0000

Data Index: 801943 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6277. Min Act: -0.0000

Data Index: 235633 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6019. Min Act: -0.0000

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5891. Min Act: -0.0000

Data Index: 716585 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6034. Min Act: -0.0000

Data Index: 658664 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1148718 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1008394 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5669. Min Act: -0.0000

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5595. Min Act: -0.0000

Data Index: 521357 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5643. Min Act: -0.0000

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5443. Min Act: -0.0000

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5648. Min Act: -0.0000

Data Index: 143615 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1055239 (C4 (Web Text))

Max Activating Token Index: 555