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

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

Neuron 2351 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 948129 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0523. Min Act: -0.0003

Data Index: 993632 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0502. Min Act: -0.0003

Data Index: 976536 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0494. Min Act: -0.0003

Data Index: 71132 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0466. Min Act: -0.0002

Data Index: 280529 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0484. Min Act: -0.0002

Data Index: 149098 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0455. Min Act: -0.0003

Data Index: 621478 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0470. Min Act: -0.0003

Data Index: 701972 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0468. Min Act: -0.0002

Data Index: 256129 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0468. Min Act: -0.0003

Data Index: 563577 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0466. Min Act: -0.0003

Data Index: 209381 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0461. Min Act: -0.0003

Data Index: 144618 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1245872 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0457. Min Act: -0.0003

Data Index: 86800 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0452. Min Act: -0.0003

Data Index: 398150 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0447. Min Act: -0.0002

Data Index: 471525 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1025797 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0445. Min Act: -0.0003

Data Index: 251457 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0003

Data Index: 480337 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0441. Min Act: -0.0003

Data Index: 873520 (C4 (Web Text))

Max Activating Token Index: 526