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

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

Neuron 2682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0465. Min Range: -1.0465

Max Act: 1.0465. Min Act: -0.0000

Data Index: 786814 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.0465. Min Range: -1.0465

Max Act: 1.0337. Min Act: -0.0000

Data Index: 32199 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9764. Min Act: -0.0001

Data Index: 811483 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9685. Min Act: -0.0001

Data Index: 326987 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1342786 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9246. Min Act: -0.0001

Data Index: 1113223 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9545. Min Act: -0.0001

Data Index: 254956 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9455. Min Act: -0.0001

Data Index: 1287995 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9428. Min Act: -0.0001

Data Index: 801865 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.9675. Min Act: -0.0001

Data Index: 568689 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8943. Min Act: -0.0001

Data Index: 827772 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8911. Min Act: -0.0001

Data Index: 44735 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8891. Min Act: -0.0001

Data Index: 531384 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8590. Min Act: -0.0001

Data Index: 818627 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1123985 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8736. Min Act: -0.0001

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8885. Min Act: -0.0001

Data Index: 840341 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8380. Min Act: -0.0001

Data Index: 1028001 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.8608. Min Act: -0.0001

Data Index: 281045 (C4 (Web Text))

Max Activating Token Index: 589