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

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

Neuron 120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1286250 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1177115 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1943. Min Act: -0.0000

Data Index: 945127 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1864. Min Act: -0.0000

Data Index: 600492 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2022. Min Act: -0.0000

Data Index: 919811 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1833. Min Act: 0.0000

Data Index: 149417 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1729. Min Act: 0.0000

Data Index: 801230 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1767. Min Act: 0.0001

Data Index: 454721 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1716. Min Act: -0.0000

Data Index: 178958 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1094861 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1113244 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1677. Min Act: -0.0001

Data Index: 625891 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1682. Min Act: -0.0000

Data Index: 620064 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1097716 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1293201 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1642. Min Act: -0.0000

Data Index: 953315 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1560. Min Act: -0.0001

Data Index: 554175 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1611. Min Act: -0.0000

Data Index: 245956 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1594. Min Act: 0.0001

Data Index: 309188 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1577. Min Act: -0.0000

Data Index: 277268 (C4 (Web Text))

Max Activating Token Index: 261