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

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

Neuron 4260 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: 2.3705. Min Range: -2.3705

Max Act: 2.3705. Min Act: -0.0000

Data Index: 290761 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 2.3705. Min Range: -2.3705

Max Act: 2.2193. Min Act: -0.0000

Data Index: 717458 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.3705. Min Range: -2.3705

Max Act: 2.1040. Min Act: -0.0000

Data Index: 526672 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 2.3705. Min Range: -2.3705

Max Act: 2.0118. Min Act: -0.0000

Data Index: 154604 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.8264. Min Act: -0.0000

Data Index: 157742 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.7487. Min Act: -0.0000

Data Index: 453123 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.8162. Min Act: -0.0000

Data Index: 1199482 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.7372. Min Act: -0.0000

Data Index: 498458 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.7376. Min Act: -0.0000

Data Index: 801068 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.7181. Min Act: -0.0000

Data Index: 562214 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.6952. Min Act: -0.0000

Data Index: 648046 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5948. Min Act: -0.0000

Data Index: 332664 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5752. Min Act: -0.0000

Data Index: 827892 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5586. Min Act: -0.0000

Data Index: 211931 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.6375. Min Act: -0.0001

Data Index: 815127 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.6318. Min Act: -0.0000

Data Index: 846492 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1166989 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.7053. Min Act: -0.0000

Data Index: 572708 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1110231 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 2.3705. Min Range: -2.3705

Max Act: 1.5757. Min Act: -0.0000

Data Index: 781199 (C4 (Web Text))

Max Activating Token Index: 492