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

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

Neuron 1857 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.6573. Min Act: -0.0002

Data Index: 1059905 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.9849. Min Act: -0.0002

Data Index: 102422 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.3107. Min Act: -0.0001

Data Index: 1032922 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.2612. Min Act: -0.0002

Data Index: 178958 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.3318. Min Act: -0.0002

Data Index: 661704 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.3812. Min Act: -0.0002

Data Index: 557016 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.2075. Min Act: -0.0002

Data Index: 864664 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1537. Min Act: -0.0001

Data Index: 397435 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1550. Min Act: -0.0002

Data Index: 1118176 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.2443. Min Act: -0.0001

Data Index: 418415 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1043. Min Act: -0.0002

Data Index: 708604 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.2675. Min Act: -0.0002

Data Index: 327688 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1913. Min Act: -0.0002

Data Index: 1120592 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1459. Min Act: -0.0002

Data Index: 1150216 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1438. Min Act: -0.0002

Data Index: 257673 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.2214. Min Act: -0.0001

Data Index: 1021860 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.0461. Min Act: -0.0002

Data Index: 1172627 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.0680. Min Act: -0.0002

Data Index: 906117 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.0493. Min Act: -0.0001

Data Index: 799250 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.9849. Min Range: -1.9849

Max Act: 1.1045. Min Act: -0.0001

Data Index: 1594920 (Python Code)

Max Activating Token Index: 18