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

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

Neuron 474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4428. Min Act: -0.0003

Data Index: 1071218 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4443. Min Act: -0.0003

Data Index: 750316 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3583. Min Act: -0.0003

Data Index: 814178 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4023. Min Act: -0.0003

Data Index: 371267 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3976. Min Act: -0.0003

Data Index: 495105 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3891. Min Act: -0.0003

Data Index: 274146 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3577. Min Act: -0.0003

Data Index: 71004 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4107. Min Act: -0.0003

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3671. Min Act: -0.0003

Data Index: 624064 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3913. Min Act: -0.0003

Data Index: 269191 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3698. Min Act: -0.0003

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3633. Min Act: -0.0003

Data Index: 867401 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3746. Min Act: -0.0003

Data Index: 672522 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.4078. Min Act: -0.0003

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3793. Min Act: -0.0003

Data Index: 1062203 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3406. Min Act: -0.0003

Data Index: 1324784 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3624. Min Act: -0.0003

Data Index: 1240778 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3269. Min Act: -0.0003

Data Index: 772643 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3602. Min Act: -0.0003

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.4443. Min Range: -0.4443

Max Act: 0.3551. Min Act: -0.0003

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 953