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

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

Neuron 2073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1295. Min Range: -2.1295

Max Act: 2.1295. Min Act: -0.0000

Data Index: 1408379 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1382651 (Python Code)

Max Activating Token Index: 735

Text #2

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1591013 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1445460 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1554516 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1488414 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.6207. Min Act: -0.0000

Data Index: 1563200 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.6528. Min Act: -0.0001

Data Index: 1447563 (Python Code)

Max Activating Token Index: 404

Text #8

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1408051 (Python Code)

Max Activating Token Index: 441

Text #9

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1469040 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1524573 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.7546. Min Act: -0.0000

Data Index: 1542678 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.4724. Min Act: -0.0001

Data Index: 1467204 (Python Code)

Max Activating Token Index: 930

Text #13

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1468051 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1449726 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5835. Min Act: -0.0000

Data Index: 1555460 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1651299 (Python Code)

Max Activating Token Index: 559

Text #17

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1407786 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1369609 (Python Code)

Max Activating Token Index: 73

Text #19

Max Range: 2.1295. Min Range: -2.1295

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1432575 (Python Code)

Max Activating Token Index: 417