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

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

Neuron 3329 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: 0.0000

Data Index: 1293187 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5971. Min Act: -0.0000

Data Index: 934824 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1204765 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5485. Min Act: -0.0000

Data Index: 748282 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5666. Min Act: -0.0000

Data Index: 450780 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5812. Min Act: -0.0000

Data Index: 838993 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5812. Min Act: -0.0000

Data Index: 849171 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5615. Min Act: -0.0000

Data Index: 886228 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5371. Min Act: -0.0000

Data Index: 657829 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1152971 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5429. Min Act: -0.0000

Data Index: 26593 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5574. Min Act: -0.0000

Data Index: 821962 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1139904 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1154367 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5170. Min Act: -0.0000

Data Index: 72931 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5525. Min Act: -0.0000

Data Index: 682802 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5117. Min Act: -0.0000

Data Index: 224261 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.4939. Min Act: -0.0000

Data Index: 884485 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5073. Min Act: -0.0000

Data Index: 610191 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.4923. Min Act: -0.0000

Data Index: 414060 (C4 (Web Text))

Max Activating Token Index: 33