Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2688 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.8942. Min Act: -0.0001

Data Index: 439098 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.8556. Min Act: -0.0000

Data Index: 547888 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.7168. Min Act: -0.0001

Data Index: 899226 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.4117. Min Act: -0.0001

Data Index: 1229536 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.4230. Min Act: -0.0001

Data Index: 850387 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.3695. Min Act: -0.0001

Data Index: 85332 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.3579. Min Act: -0.0001

Data Index: 59895 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.3044. Min Act: -0.0001

Data Index: 381658 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.2736. Min Act: -0.0001

Data Index: 814814 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.2956. Min Act: -0.0001

Data Index: 640362 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1949. Min Act: -0.0001

Data Index: 87976 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.2140. Min Act: -0.0001

Data Index: 1055388 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1560. Min Act: -0.0001

Data Index: 1139653 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1026785 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1691. Min Act: -0.0001

Data Index: 32678 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.0954. Min Act: -0.0001

Data Index: 543681 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1520. Min Act: -0.0001

Data Index: 259485 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.0458. Min Act: -0.0001

Data Index: 731009 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.0811. Min Act: -0.0001

Data Index: 690432 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.8942. Min Range: -1.8942

Max Act: 1.1229. Min Act: -0.0001

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 713