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

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

Neuron 2580 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: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 602374 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0645. Min Act: -0.0001

Data Index: 475380 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0629. Min Act: -0.0001

Data Index: 964734 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0598. Min Act: -0.0001

Data Index: 963700 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0590. Min Act: -0.0001

Data Index: 121247 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0572. Min Act: -0.0001

Data Index: 40318 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1306144 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0599. Min Act: -0.0001

Data Index: 10352 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0595. Min Act: -0.0001

Data Index: 26076 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1253330 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1180616 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0567. Min Act: -0.0001

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0552. Min Act: -0.0001

Data Index: 373921 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1341530 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0522. Min Act: -0.0001

Data Index: 511039 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0534. Min Act: -0.0001

Data Index: 5087 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0519. Min Act: -0.0001

Data Index: 256064 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0529. Min Act: -0.0001

Data Index: 416756 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0546. Min Act: -0.0001

Data Index: 349253 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0506. Min Act: -0.0001

Data Index: 932390 (C4 (Web Text))

Max Activating Token Index: 668