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

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

Neuron 633 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0001

Data Index: 731159 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0435. Min Act: -0.0001

Data Index: 439518 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1269702 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0496. Min Act: -0.0001

Data Index: 179623 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1169198 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0503. Min Act: -0.0001

Data Index: 241638 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0518. Min Act: -0.0001

Data Index: 995010 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0483. Min Act: -0.0001

Data Index: 362683 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0366. Min Act: -0.0001

Data Index: 514946 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0479. Min Act: -0.0001

Data Index: 784455 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0508. Min Act: -0.0001

Data Index: 436488 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0466. Min Act: -0.0001

Data Index: 757272 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0470. Min Act: -0.0001

Data Index: 674251 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1147879 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1126724 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0471. Min Act: -0.0001

Data Index: 428200 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0456. Min Act: -0.0001

Data Index: 403817 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1078759 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0461. Min Act: -0.0001

Data Index: 580916 (C4 (Web Text))

Max Activating Token Index: 910