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

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

Neuron 389 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1544931 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6528. Min Act: -0.0000

Data Index: 300340 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6097. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1167839 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5756. Min Act: -0.0000

Data Index: 684252 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5973. Min Act: -0.0000

Data Index: 748625 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5838. Min Act: -0.0000

Data Index: 45108 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1621756 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1641636 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5345. Min Act: -0.0000

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1154176 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5559. Min Act: -0.0000

Data Index: 193671 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5007. Min Act: -0.0000

Data Index: 369349 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5088. Min Act: -0.0000

Data Index: 668372 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1313108 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1628628 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4899. Min Act: -0.0000

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1557062 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4441. Min Act: -0.0000

Data Index: 137419 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4813. Min Act: -0.0000

Data Index: 203117 (C4 (Web Text))

Max Activating Token Index: 374