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

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

Neuron 72 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: 2.1061. Min Range: -2.1061

Max Act: 2.1061. Min Act: -0.0000

Data Index: 546367 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1017791 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.9100. Min Act: -0.0000

Data Index: 578847 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.8207. Min Act: -0.0001

Data Index: 1059685 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1111676 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5815. Min Act: -0.0000

Data Index: 642303 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1098500 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5042. Min Act: -0.0000

Data Index: 518498 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.6720. Min Act: -0.0000

Data Index: 295135 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5701. Min Act: -0.0001

Data Index: 1089972 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1127955 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5779. Min Act: -0.0001

Data Index: 1215770 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1040365 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1138814 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5131. Min Act: -0.0000

Data Index: 313378 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.4310. Min Act: -0.0000

Data Index: 646202 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1079703 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1026289 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5150. Min Act: -0.0001

Data Index: 255655 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.1061. Min Range: -2.1061

Max Act: 1.5319. Min Act: -0.0000

Data Index: 350196 (C4 (Web Text))

Max Activating Token Index: 905