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

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

Neuron 1559 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4247. Min Act: -0.0001

Data Index: 1382590 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1511641 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1627302 (Python Code)

Max Activating Token Index: 306

Text #3

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3649. Min Act: -0.0001

Data Index: 1363816 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3874. Min Act: -0.0001

Data Index: 1544062 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1640020 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3711. Min Act: -0.0001

Data Index: 1435553 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3807. Min Act: -0.0001

Data Index: 1383253 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1540431 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3841. Min Act: -0.0001

Data Index: 1470131 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1572946 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3588. Min Act: -0.0001

Data Index: 1407443 (Python Code)

Max Activating Token Index: 106

Text #12

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3590. Min Act: -0.0001

Data Index: 1652293 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1390309 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3528. Min Act: -0.0001

Data Index: 1625398 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1454061 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1547837 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3339. Min Act: -0.0001

Data Index: 1370921 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1460533 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1383394 (Python Code)

Max Activating Token Index: 219