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

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

Neuron 2027 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6994. Min Act: -0.0002

Data Index: 1057314 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.7129. Min Act: -0.0002

Data Index: 1293324 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6699. Min Act: -0.0002

Data Index: 1303395 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6719. Min Act: -0.0002

Data Index: 695824 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6787. Min Act: -0.0001

Data Index: 199578 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6610. Min Act: -0.0002

Data Index: 691551 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6318. Min Act: -0.0001

Data Index: 632404 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6481. Min Act: -0.0002

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6329. Min Act: -0.0001

Data Index: 335751 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6058. Min Act: -0.0002

Data Index: 655323 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6501. Min Act: -0.0001

Data Index: 36315 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6089. Min Act: -0.0002

Data Index: 672178 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6419. Min Act: -0.0002

Data Index: 117708 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6163. Min Act: -0.0002

Data Index: 20610 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6031. Min Act: -0.0001

Data Index: 630734 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1584355 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6183. Min Act: -0.0002

Data Index: 636084 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.6294. Min Act: -0.0002

Data Index: 1116816 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5974. Min Act: -0.0002

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5918. Min Act: -0.0002

Data Index: 963549 (C4 (Web Text))

Max Activating Token Index: 557