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

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

Neuron 3088 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: 5.6706. Min Range: -5.6706

Max Act: 5.6706. Min Act: -0.0000

Data Index: 22424 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.4698. Min Act: -0.0000

Data Index: 498130 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.4091. Min Act: -0.0000

Data Index: 332879 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.4134. Min Act: -0.0000

Data Index: 933749 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.2905. Min Act: -0.0000

Data Index: 1199326 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.1616. Min Act: -0.0000

Data Index: 372194 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 5.6706. Min Range: -5.6706

Max Act: 5.0035. Min Act: -0.0000

Data Index: 300981 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.7921. Min Act: -0.0000

Data Index: 716971 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.8343. Min Act: -0.0000

Data Index: 615214 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.8583. Min Act: -0.0000

Data Index: 168658 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.6503. Min Act: -0.0000

Data Index: 100632 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.3750. Min Act: -0.0000

Data Index: 581952 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.2927. Min Act: -0.0000

Data Index: 596039 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.1197. Min Act: -0.0000

Data Index: 1343687 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.5032. Min Act: -0.0000

Data Index: 690378 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.3194. Min Act: -0.0000

Data Index: 263208 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.2577. Min Act: -0.0000

Data Index: 515570 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.3971. Min Act: -0.0000

Data Index: 800670 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 5.6706. Min Range: -5.6706

Max Act: 4.2130. Min Act: -0.0000

Data Index: 814071 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 5.6706. Min Range: -5.6706

Max Act: 3.8046. Min Act: -0.0000

Data Index: 172192 (C4 (Web Text))

Max Activating Token Index: 422