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

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

Neuron 3948 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.9312. Min Act: -0.0001

Data Index: 695816 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1010682 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8131. Min Act: -0.0001

Data Index: 20436 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8605. Min Act: -0.0001

Data Index: 308332 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1347372 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8299. Min Act: -0.0001

Data Index: 257519 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7218. Min Act: -0.0001

Data Index: 412328 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7645. Min Act: -0.0001

Data Index: 433855 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6745. Min Act: -0.0001

Data Index: 409634 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7289. Min Act: -0.0001

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6689. Min Act: -0.0001

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7554. Min Act: -0.0001

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1229921 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1338388 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6471. Min Act: -0.0001

Data Index: 620746 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6550. Min Act: -0.0001

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6531. Min Act: -0.0001

Data Index: 417910 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1484789 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6120. Min Act: -0.0001

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 147