Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.4980. Min Range: -4.4980

Max Act: 4.3313. Min Act: -0.0001

Data Index: 1030169 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 4.4980. Min Range: -4.4980

Max Act: 4.4980. Min Act: -0.0000

Data Index: 1226495 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 4.4980. Min Range: -4.4980

Max Act: 4.2675. Min Act: -0.0001

Data Index: 1188131 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.7127. Min Act: -0.0001

Data Index: 676498 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.6053. Min Act: -0.0001

Data Index: 1198676 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.9310. Min Act: -0.0001

Data Index: 426595 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 4.4980. Min Range: -4.4980

Max Act: 4.0412. Min Act: -0.0001

Data Index: 918305 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.9238. Min Act: -0.0000

Data Index: 980208 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.5717. Min Act: -0.0001

Data Index: 1063980 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.5305. Min Act: -0.0001

Data Index: 11435 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.6712. Min Act: -0.0001

Data Index: 1301354 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.5020. Min Act: -0.0000

Data Index: 287807 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.5952. Min Act: -0.0001

Data Index: 1037417 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.3670. Min Act: -0.0001

Data Index: 262773 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.5245. Min Act: -0.0001

Data Index: 695149 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.7067. Min Act: -0.0001

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 4.4980. Min Range: -4.4980

Max Act: 2.8495. Min Act: -0.0001

Data Index: 495320 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.2643. Min Act: -0.0001

Data Index: 862733 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.3923. Min Act: -0.0001

Data Index: 669770 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 4.4980. Min Range: -4.4980

Max Act: 3.3718. Min Act: -0.0001

Data Index: 264112 (C4 (Web Text))

Max Activating Token Index: 303