Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4641. Min Range: -2.4641

Max Act: 2.4641. Min Act: -0.0000

Data Index: 1035125 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 2.4641. Min Range: -2.4641

Max Act: 2.1270. Min Act: -0.0000

Data Index: 650422 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.4641. Min Range: -2.4641

Max Act: 2.0106. Min Act: -0.0000

Data Index: 1142415 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8750. Min Act: -0.0000

Data Index: 1246206 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1174672 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9347. Min Act: -0.0000

Data Index: 784362 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1220745 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9040. Min Act: -0.0000

Data Index: 1205182 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9943. Min Act: -0.0000

Data Index: 1283240 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8720. Min Act: -0.0000

Data Index: 350164 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8750. Min Act: -0.0000

Data Index: 665150 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9940. Min Act: -0.0000

Data Index: 953460 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8692. Min Act: -0.0000

Data Index: 810292 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1233479 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.9810. Min Act: -0.0000

Data Index: 712914 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8601. Min Act: -0.0000

Data Index: 406718 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8602. Min Act: -0.0000

Data Index: 1147344 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.8409. Min Act: -0.0000

Data Index: 239419 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.7244. Min Act: -0.0000

Data Index: 750710 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 2.4641. Min Range: -2.4641

Max Act: 1.7174. Min Act: -0.0000

Data Index: 12874 (C4 (Web Text))

Max Activating Token Index: 893