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

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

Neuron 357 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: 0.7369. Min Range: -0.7369

Max Act: 0.7213. Min Act: 0.0000

Data Index: 1087438 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1159253 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6448. Min Act: 0.0001

Data Index: 1174780 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6466. Min Act: -0.0000

Data Index: 375209 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1047215 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5935. Min Act: -0.0000

Data Index: 313615 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5850. Min Act: -0.0000

Data Index: 620815 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6048. Min Act: -0.0000

Data Index: 997035 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5785. Min Act: -0.0000

Data Index: 169111 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1082023 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5618. Min Act: -0.0000

Data Index: 235225 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5482. Min Act: -0.0000

Data Index: 247395 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5146. Min Act: -0.0000

Data Index: 743439 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1072952 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1083394 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4884. Min Act: -0.0000

Data Index: 115439 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5058. Min Act: -0.0000

Data Index: 588606 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4848. Min Act: -0.0000

Data Index: 751056 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1237795 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5080. Min Act: -0.0000

Data Index: 878227 (C4 (Web Text))

Max Activating Token Index: 315