Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2394 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.0316. Min Act: -0.0003

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.1169. Min Range: -1.1169

Max Act: 1.1169. Min Act: -0.0003

Data Index: 590901 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9493. Min Act: -0.0003

Data Index: 238407 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9484. Min Act: -0.0003

Data Index: 733889 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9677. Min Act: -0.0003

Data Index: 407737 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9253. Min Act: -0.0003

Data Index: 431087 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8790. Min Act: -0.0004

Data Index: 525238 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.9035. Min Act: -0.0003

Data Index: 257360 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8438. Min Act: -0.0003

Data Index: 630940 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8273. Min Act: -0.0003

Data Index: 1172496 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8663. Min Act: -0.0003

Data Index: 434350 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8021. Min Act: -0.0003

Data Index: 451071 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8232. Min Act: -0.0003

Data Index: 174504 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7729. Min Act: -0.0003

Data Index: 670096 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7938. Min Act: -0.0003

Data Index: 766558 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7938. Min Act: -0.0003

Data Index: 1355605 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7664. Min Act: -0.0003

Data Index: 826833 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7862. Min Act: -0.0003

Data Index: 858865 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.8067. Min Act: -0.0003

Data Index: 1127520 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.1169. Min Range: -1.1169

Max Act: 0.7755. Min Act: -0.0003

Data Index: 1087396 (C4 (Web Text))

Max Activating Token Index: 290