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

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

Neuron 1473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.6486. Min Act: -0.0000

Data Index: 715375 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.6142. Min Act: -0.0000

Data Index: 807618 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.4902. Min Act: -0.0000

Data Index: 1247922 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.5259. Min Act: -0.0000

Data Index: 1079724 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1305552 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.4050. Min Act: -0.0000

Data Index: 901949 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.3246. Min Act: -0.0000

Data Index: 19912 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.1803. Min Act: -0.0000

Data Index: 9795 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.2728. Min Act: -0.0000

Data Index: 602226 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 2.6486. Min Range: -2.6486

Max Act: 2.1366. Min Act: -0.0000

Data Index: 1115167 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.9695. Min Act: -0.0000

Data Index: 892076 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8406. Min Act: -0.0000

Data Index: 531258 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8284. Min Act: -0.0000

Data Index: 850005 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8239. Min Act: -0.0001

Data Index: 512185 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8072. Min Act: -0.0000

Data Index: 1048297 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.9034. Min Act: -0.0000

Data Index: 353305 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8998. Min Act: -0.0000

Data Index: 640515 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.8858. Min Act: -0.0000

Data Index: 655047 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.7489. Min Act: -0.0000

Data Index: 1083897 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.6486. Min Range: -2.6486

Max Act: 1.7550. Min Act: -0.0000

Data Index: 864479 (C4 (Web Text))

Max Activating Token Index: 828