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

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

Neuron 1708 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: 1.3227. Min Range: -1.3227

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1173023 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.1982. Min Act: -0.0000

Data Index: 659591 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1349558 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0034. Min Act: -0.0000

Data Index: 233055 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1122626 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9465. Min Act: -0.0000

Data Index: 338477 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1110322 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8747. Min Act: -0.0000

Data Index: 748314 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8272. Min Act: -0.0000

Data Index: 307210 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8898. Min Act: -0.0000

Data Index: 995605 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8731. Min Act: -0.0000

Data Index: 227977 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9010. Min Act: -0.0000

Data Index: 539123 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8916. Min Act: -0.0000

Data Index: 342640 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8940. Min Act: -0.0000

Data Index: 644616 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8222. Min Act: -0.0000

Data Index: 201414 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1078840 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1086297 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8451. Min Act: -0.0000

Data Index: 229166 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9209. Min Act: -0.0000

Data Index: 276553 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1282181 (C4 (Web Text))

Max Activating Token Index: 761