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

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

Neuron 2733 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1127810 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1207355 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1943. Min Act: -0.0000

Data Index: 90147 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1056. Min Act: -0.0000

Data Index: 239037 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9782. Min Act: -0.0000

Data Index: 328022 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0073. Min Act: -0.0000

Data Index: 316801 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9276. Min Act: -0.0000

Data Index: 417052 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9206. Min Act: -0.0000

Data Index: 942388 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8746. Min Act: -0.0000

Data Index: 358594 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8451. Min Act: -0.0000

Data Index: 857896 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1287787 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8560. Min Act: -0.0000

Data Index: 202317 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9380. Min Act: -0.0000

Data Index: 49209 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8069. Min Act: -0.0000

Data Index: 962519 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.7605. Min Act: -0.0000

Data Index: 646363 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8040. Min Act: -0.0000

Data Index: 770290 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1202827 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.7692. Min Act: -0.0000

Data Index: 628053 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.7317. Min Act: -0.0000

Data Index: 926013 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1335940 (C4 (Web Text))

Max Activating Token Index: 112