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

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

Neuron 72 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0001

Data Index: 970087 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1335008 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0579. Min Act: -0.0001

Data Index: 222380 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1020336 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0657. Min Act: -0.0001

Data Index: 539728 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0560. Min Act: -0.0001

Data Index: 752700 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1029957 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1017088 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1169459 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0547. Min Act: -0.0001

Data Index: 261944 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0524. Min Act: -0.0001

Data Index: 172971 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0522. Min Act: -0.0001

Data Index: 543844 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0491. Min Act: -0.0001

Data Index: 201115 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0511. Min Act: -0.0001

Data Index: 589049 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0487. Min Act: -0.0001

Data Index: 863781 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1113619 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1355503 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0465. Min Act: -0.0001

Data Index: 839511 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1144790 (C4 (Web Text))

Max Activating Token Index: 916