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

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

Neuron 1424 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: 0.6601. Min Range: -0.6601

Max Act: 0.5862. Min Act: -0.0000

Data Index: 238472 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.6601. Min Act: -0.0000

Data Index: 919559 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1156419 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1118588 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5273. Min Act: -0.0000

Data Index: 567573 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4730. Min Act: -0.0000

Data Index: 299916 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5680. Min Act: -0.0000

Data Index: 774318 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5579. Min Act: -0.0000

Data Index: 282004 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5422. Min Act: -0.0000

Data Index: 153572 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5534. Min Act: -0.0000

Data Index: 452884 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5278. Min Act: -0.0000

Data Index: 587473 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1033977 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5253. Min Act: -0.0000

Data Index: 460181 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4930. Min Act: -0.0000

Data Index: 534667 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1351915 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5675. Min Act: -0.0000

Data Index: 568921 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4870. Min Act: -0.0000

Data Index: 301565 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1076917 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.4963. Min Act: -0.0000

Data Index: 244636 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.6601. Min Range: -0.6601

Max Act: 0.5188. Min Act: -0.0000

Data Index: 315646 (C4 (Web Text))

Max Activating Token Index: 655