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

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

Neuron 249 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: 0.8835. Min Range: -0.8835

Max Act: 0.8835. Min Act: -0.0001

Data Index: 378461 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7525. Min Act: -0.0001

Data Index: 165541 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7775. Min Act: -0.0001

Data Index: 58269 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1286026 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7585. Min Act: -0.0001

Data Index: 47018 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7287. Min Act: -0.0001

Data Index: 1308296 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8250. Min Act: -0.0002

Data Index: 127393 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7216. Min Act: -0.0001

Data Index: 454517 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8102. Min Act: -0.0001

Data Index: 749805 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7858. Min Act: -0.0002

Data Index: 1217657 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7225. Min Act: -0.0001

Data Index: 1218161 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6526. Min Act: -0.0002

Data Index: 815765 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7652. Min Act: -0.0002

Data Index: 321341 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7691. Min Act: -0.0002

Data Index: 1257903 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7708. Min Act: -0.0001

Data Index: 112056 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7022. Min Act: -0.0002

Data Index: 62721 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7612. Min Act: -0.0002

Data Index: 494489 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7374. Min Act: -0.0001

Data Index: 266207 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7141. Min Act: -0.0002

Data Index: 611512 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6969. Min Act: -0.0002

Data Index: 835854 (C4 (Web Text))

Max Activating Token Index: 918