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

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

Neuron 2367 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3053. Min Act: -0.0001

Data Index: 941249 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1259756 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1397314 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2417. Min Act: -0.0001

Data Index: 190806 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2338. Min Act: -0.0001

Data Index: 563090 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2367. Min Act: -0.0001

Data Index: 23485 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2289. Min Act: -0.0001

Data Index: 742208 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2276. Min Act: -0.0001

Data Index: 319384 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2250. Min Act: -0.0000

Data Index: 188921 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1254094 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1482922 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2134. Min Act: -0.0000

Data Index: 788486 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1971. Min Act: -0.0000

Data Index: 630764 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2037. Min Act: -0.0000

Data Index: 304546 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1389079 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2026. Min Act: -0.0001

Data Index: 235425 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1943. Min Act: -0.0000

Data Index: 358225 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1563554 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1568821 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2165. Min Act: -0.0001

Data Index: 306766 (C4 (Web Text))

Max Activating Token Index: 785