Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1014 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3733. Min Act: -0.0001

Data Index: 1239256 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1652119 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3296. Min Act: -0.0001

Data Index: 911599 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1469711 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3242. Min Act: -0.0001

Data Index: 1343670 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3450. Min Act: -0.0001

Data Index: 119775 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1575369 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3528. Min Act: -0.0001

Data Index: 1537279 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3210. Min Act: -0.0001

Data Index: 157883 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3229. Min Act: -0.0001

Data Index: 928402 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1628552 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1417994 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1364583 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3209. Min Act: -0.0001

Data Index: 998621 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3163. Min Act: -0.0001

Data Index: 301016 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3166. Min Act: -0.0001

Data Index: 1496526 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1365907 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3048. Min Act: -0.0001

Data Index: 721617 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3140. Min Act: -0.0001

Data Index: 1545910 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1611610 (Python Code)

Max Activating Token Index: 40