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

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

Neuron 4482 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3735. Min Act: -0.0001

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2910. Min Act: -0.0001

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2371. Min Act: -0.0001

Data Index: 1236544 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2579. Min Act: -0.0001

Data Index: 83083 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1630879 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3163. Min Act: -0.0001

Data Index: 359343 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2330. Min Act: -0.0001

Data Index: 1439188 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2589. Min Act: -0.0001

Data Index: 942816 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2586. Min Act: -0.0001

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2450. Min Act: -0.0001

Data Index: 1214006 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2229. Min Act: -0.0001

Data Index: 487019 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2015. Min Act: -0.0001

Data Index: 793442 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2071. Min Act: -0.0001

Data Index: 367157 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.1921. Min Act: -0.0001

Data Index: 820258 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2072. Min Act: -0.0001

Data Index: 722862 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2020. Min Act: -0.0001

Data Index: 322210 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2700. Min Act: -0.0001

Data Index: 117212 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2134. Min Act: -0.0001

Data Index: 280917 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.1970. Min Act: -0.0001

Data Index: 537522 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2144. Min Act: -0.0001

Data Index: 562789 (C4 (Web Text))

Max Activating Token Index: 391