Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1164 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.4093. Min Act: -0.0002

Data Index: 770502 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3500. Min Act: -0.0002

Data Index: 433051 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2342. Min Act: -0.0002

Data Index: 528676 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2568. Min Act: -0.0002

Data Index: 313371 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2910. Min Act: -0.0002

Data Index: 628817 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2357. Min Act: -0.0002

Data Index: 852785 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2542. Min Act: -0.0002

Data Index: 1427461 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2095. Min Act: -0.0002

Data Index: 583030 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2295. Min Act: -0.0002

Data Index: 138586 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2367. Min Act: -0.0002

Data Index: 1559422 (Python Code)

Max Activating Token Index: 455

Text #10

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1374. Min Act: -0.0002

Data Index: 922981 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1274088 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1663. Min Act: -0.0002

Data Index: 1249367 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1815. Min Act: -0.0002

Data Index: 842576 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1939. Min Act: -0.0002

Data Index: 800542 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2191. Min Act: -0.0002

Data Index: 470633 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1958. Min Act: -0.0002

Data Index: 1527796 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1994. Min Act: -0.0002

Data Index: 1383581 (Python Code)

Max Activating Token Index: 922

Text #18

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2362. Min Act: -0.0002

Data Index: 1134410 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.1919. Min Act: -0.0002

Data Index: 181823 (C4 (Web Text))

Max Activating Token Index: 355