Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1997 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3291. Min Act: -0.0004

Data Index: 291751 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2715. Min Act: -0.0004

Data Index: 883284 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2541. Min Act: -0.0004

Data Index: 1192335 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2785. Min Act: -0.0004

Data Index: 548484 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2802. Min Act: -0.0004

Data Index: 743594 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2776. Min Act: -0.0004

Data Index: 1313043 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2949. Min Act: -0.0004

Data Index: 1357814 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2532. Min Act: -0.0004

Data Index: 606218 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3108. Min Act: -0.0004

Data Index: 891986 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2493. Min Act: -0.0004

Data Index: 296763 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2419. Min Act: -0.0004

Data Index: 872290 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2722. Min Act: -0.0004

Data Index: 1316735 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2923. Min Act: -0.0004

Data Index: 32775 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2681. Min Act: -0.0004

Data Index: 468408 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2582. Min Act: -0.0004

Data Index: 439616 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2475. Min Act: -0.0004

Data Index: 1152323 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2469. Min Act: -0.0004

Data Index: 918619 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2344. Min Act: -0.0004

Data Index: 445164 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2510. Min Act: -0.0004

Data Index: 1189644 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2588. Min Act: -0.0004

Data Index: 774695 (C4 (Web Text))

Max Activating Token Index: 73