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

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

Neuron 1276 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: 0.5593. Min Range: -0.5593

Max Act: 0.5593. Min Act: -0.0004

Data Index: 1573127 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5497. Min Act: -0.0004

Data Index: 1245536 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5286. Min Act: -0.0004

Data Index: 1258011 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5076. Min Act: -0.0004

Data Index: 755197 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5447. Min Act: -0.0004

Data Index: 968433 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4790. Min Act: -0.0004

Data Index: 1630362 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4948. Min Act: -0.0004

Data Index: 741856 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4986. Min Act: -0.0004

Data Index: 406236 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4804. Min Act: -0.0004

Data Index: 802392 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5305. Min Act: -0.0004

Data Index: 906393 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4297. Min Act: -0.0004

Data Index: 437477 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5225. Min Act: -0.0004

Data Index: 344491 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4996. Min Act: -0.0004

Data Index: 730465 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5537. Min Act: -0.0004

Data Index: 1183270 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4510. Min Act: -0.0004

Data Index: 132109 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4939. Min Act: -0.0004

Data Index: 561276 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4865. Min Act: -0.0004

Data Index: 697914 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5025. Min Act: -0.0004

Data Index: 215976 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4503. Min Act: -0.0004

Data Index: 987695 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4647. Min Act: -0.0004

Data Index: 716559 (C4 (Web Text))

Max Activating Token Index: 1021