Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6865. Min Act: -0.0002

Data Index: 227866 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6935. Min Act: -0.0002

Data Index: 1266232 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6423. Min Act: -0.0002

Data Index: 348564 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6227. Min Act: -0.0002

Data Index: 1211741 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4320. Min Act: -0.0002

Data Index: 1313824 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6063. Min Act: -0.0002

Data Index: 1020411 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5542. Min Act: -0.0002

Data Index: 579122 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4332. Min Act: -0.0002

Data Index: 573441 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4997. Min Act: -0.0002

Data Index: 1172848 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5051. Min Act: -0.0002

Data Index: 709128 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5485. Min Act: -0.0002

Data Index: 1100494 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4437. Min Act: -0.0002

Data Index: 750804 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5880. Min Act: -0.0002

Data Index: 507506 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4140. Min Act: -0.0002

Data Index: 264227 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3886. Min Act: -0.0002

Data Index: 1218637 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5011. Min Act: -0.0002

Data Index: 881394 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3744. Min Act: -0.0002

Data Index: 1094132 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4609. Min Act: -0.0002

Data Index: 1123801 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4106. Min Act: -0.0002

Data Index: 370286 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4534. Min Act: -0.0002

Data Index: 64250 (C4 (Web Text))

Max Activating Token Index: 569