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

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

Neuron 2026 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: 2.0600. Min Range: -2.0600

Max Act: 2.0164. Min Act: -0.0001

Data Index: 733034 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.9573. Min Act: -0.0001

Data Index: 1306312 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.0600. Min Range: -2.0600

Max Act: 2.0600. Min Act: -0.0001

Data Index: 451702 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.9523. Min Act: -0.0001

Data Index: 628124 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7635. Min Act: -0.0000

Data Index: 222922 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7369. Min Act: -0.0001

Data Index: 797036 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6640. Min Act: -0.0001

Data Index: 1152880 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7240. Min Act: -0.0001

Data Index: 1269115 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6550. Min Act: -0.0001

Data Index: 1334159 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6629. Min Act: -0.0001

Data Index: 1340973 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6605. Min Act: -0.0000

Data Index: 218117 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6471. Min Act: -0.0001

Data Index: 1203821 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5532. Min Act: -0.0000

Data Index: 329613 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5486. Min Act: -0.0001

Data Index: 47029 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5485. Min Act: -0.0001

Data Index: 184009 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5445. Min Act: -0.0001

Data Index: 476610 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5721. Min Act: -0.0001

Data Index: 780600 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5751. Min Act: -0.0001

Data Index: 368567 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5627. Min Act: -0.0001

Data Index: 972685 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5091. Min Act: -0.0001

Data Index: 89905 (C4 (Web Text))

Max Activating Token Index: 517