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

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

Neuron 2993 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: 0.8142. Min Range: -0.8142

Max Act: 0.8142. Min Act: 0.0000

Data Index: 1363776 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1497074 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1536321 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6940. Min Act: -0.0001

Data Index: 1599734 (Python Code)

Max Activating Token Index: 311

Text #4

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1580497 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1375849 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6669. Min Act: 0.0001

Data Index: 1634294 (Python Code)

Max Activating Token Index: 651

Text #7

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6423. Min Act: 0.0002

Data Index: 1561650 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6635. Min Act: 0.0002

Data Index: 1441307 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1500717 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1423746 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6332. Min Act: 0.0000

Data Index: 1516721 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1393861 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6190. Min Act: 0.0002

Data Index: 1477460 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6036. Min Act: 0.0002

Data Index: 1437085 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1566108 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5801. Min Act: 0.0002

Data Index: 1588727 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1588304 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5675. Min Act: -0.0001

Data Index: 1576065 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1429058 (Python Code)

Max Activating Token Index: 218