Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 678 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 4.5103. Min Range: -4.5103

Max Act: 4.5103. Min Act: -0.0003

Data Index: 295932 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 4.5103. Min Range: -4.5103

Max Act: 4.1795. Min Act: -0.0004

Data Index: 488022 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 4.5103. Min Range: -4.5103

Max Act: 4.0991. Min Act: -0.0004

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.5103. Min Range: -4.5103

Max Act: 4.0928. Min Act: -0.0004

Data Index: 1187283 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.8300. Min Act: -0.0004

Data Index: 1155886 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.9299. Min Act: -0.0004

Data Index: 993044 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.7977. Min Act: -0.0004

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.5687. Min Act: -0.0004

Data Index: 108837 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.6994. Min Act: -0.0004

Data Index: 298413 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.6676. Min Act: -0.0004

Data Index: 423777 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.6450. Min Act: -0.0004

Data Index: 55006 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.5811. Min Act: -0.0004

Data Index: 238168 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.5147. Min Act: -0.0004

Data Index: 1181073 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.5154. Min Act: -0.0003

Data Index: 1192341 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.3713. Min Act: -0.0004

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.3574. Min Act: -0.0003

Data Index: 408373 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.3458. Min Act: -0.0004

Data Index: 12612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.1376. Min Act: -0.0004

Data Index: 566409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.1157. Min Act: -0.0004

Data Index: 259302 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 4.5103. Min Range: -4.5103

Max Act: 3.1126. Min Act: -0.0004

Data Index: 933348 (C4 (Web Text))

Max Activating Token Index: 697