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

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

Neuron 1435 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: 0.4189. Min Range: -0.4189

Max Act: 0.4189. Min Act: -0.0000

Data Index: 405403 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1354401 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3941. Min Act: -0.0000

Data Index: 406213 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1247131 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3700. Min Act: -0.0000

Data Index: 263223 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1342030 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3699. Min Act: -0.0000

Data Index: 247674 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3739. Min Act: -0.0000

Data Index: 27414 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3600. Min Act: -0.0000

Data Index: 93960 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3553. Min Act: -0.0000

Data Index: 540165 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1192708 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3437. Min Act: -0.0000

Data Index: 485389 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3312. Min Act: -0.0000

Data Index: 45860 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3303. Min Act: -0.0000

Data Index: 409500 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3298. Min Act: -0.0000

Data Index: 941792 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3272. Min Act: -0.0000

Data Index: 389824 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3364. Min Act: -0.0000

Data Index: 783997 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3433. Min Act: -0.0000

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1083848 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.4189. Min Range: -0.4189

Max Act: 0.3360. Min Act: -0.0000

Data Index: 989321 (C4 (Web Text))

Max Activating Token Index: 173