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

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

Neuron 1815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1298139 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2835. Min Act: -0.0001

Data Index: 592795 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2751. Min Act: -0.0001

Data Index: 208997 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2693. Min Act: -0.0001

Data Index: 673081 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2549. Min Act: -0.0001

Data Index: 601940 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2558. Min Act: -0.0001

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2680. Min Act: -0.0001

Data Index: 728169 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1297985 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2436. Min Act: -0.0001

Data Index: 428714 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1105163 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2579. Min Act: -0.0001

Data Index: 547487 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2387. Min Act: -0.0001

Data Index: 159436 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2620. Min Act: -0.0001

Data Index: 468802 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2400. Min Act: -0.0001

Data Index: 517785 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2332. Min Act: -0.0001

Data Index: 24342 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2404. Min Act: -0.0001

Data Index: 118978 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2351. Min Act: -0.0001

Data Index: 955536 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1175213 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3097. Min Range: -0.3097

Max Act: 0.2258. Min Act: -0.0001

Data Index: 722088 (C4 (Web Text))

Max Activating Token Index: 347