Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.8000. Min Act: -0.0000

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.6306. Min Act: -0.0000

Data Index: 1257908 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1121587 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.4659. Min Act: -0.0000

Data Index: 1089501 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.4235. Min Act: -0.0000

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3843. Min Act: -0.0000

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3668. Min Act: -0.0000

Data Index: 1128342 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3776. Min Act: -0.0000

Data Index: 130699 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.1824. Min Act: -0.0000

Data Index: 396902 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.2032. Min Act: -0.0000

Data Index: 786932 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.9414. Min Act: -0.0000

Data Index: 428819 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0661. Min Act: -0.0000

Data Index: 732266 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.8326. Min Act: -0.0000

Data Index: 576968 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.9204. Min Act: -0.0000

Data Index: 869237 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.9192. Min Act: -0.0000

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.7604. Min Act: -0.0000

Data Index: 299174 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.7653. Min Act: -0.0000

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.8536. Min Act: -0.0000

Data Index: 796495 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.7408. Min Act: -0.0000

Data Index: 64433 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.8470. Min Act: -0.0000

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 722