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

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

Neuron 5541 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.3462. Min Act: -0.0000

Data Index: 588502 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.2792. Min Act: -0.0000

Data Index: 194585 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0543. Min Act: -0.0000

Data Index: 574282 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.1136. Min Act: -0.0000

Data Index: 341064 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1248144 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0660. Min Act: -0.0000

Data Index: 804475 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0402. Min Act: -0.0000

Data Index: 976552 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.1226. Min Act: -0.0000

Data Index: 1241470 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8991. Min Act: -0.0000

Data Index: 220203 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8547. Min Act: -0.0000

Data Index: 23435 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1065269 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0496. Min Act: -0.0000

Data Index: 144133 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8213. Min Act: -0.0000

Data Index: 174585 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 2.3462. Min Range: -2.3462

Max Act: 2.0138. Min Act: -0.0000

Data Index: 581693 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8832. Min Act: -0.0000

Data Index: 140820 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8826. Min Act: -0.0000

Data Index: 111864 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8694. Min Act: -0.0000

Data Index: 608373 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.7689. Min Act: -0.0000

Data Index: 597400 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1098198 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 2.3462. Min Range: -2.3462

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1044363 (C4 (Web Text))

Max Activating Token Index: 530