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

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

Neuron 3455 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: 0.1220. Min Range: -0.1220

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1575713 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1257445 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1324266 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1442113 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1163. Min Act: -0.0000

Data Index: 670433 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1117. Min Act: -0.0001

Data Index: 466327 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1133. Min Act: -0.0000

Data Index: 146622 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1576353 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1038. Min Act: -0.0000

Data Index: 408546 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1050. Min Act: -0.0000

Data Index: 377569 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1655751 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0965. Min Act: -0.0000

Data Index: 848061 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1379026 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1505110 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1131859 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0931. Min Act: -0.0000

Data Index: 922153 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0878. Min Act: -0.0000

Data Index: 307383 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0922. Min Act: -0.0000

Data Index: 725348 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1429631 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0866. Min Act: -0.0001

Data Index: 885407 (C4 (Web Text))

Max Activating Token Index: 965