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

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

Neuron 1953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5229. Min Range: -3.5229

Max Act: 3.4157. Min Act: -0.0001

Data Index: 424255 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.5229. Min Range: -3.5229

Max Act: 3.5229. Min Act: -0.0001

Data Index: 454849 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 3.5229. Min Range: -3.5229

Max Act: 3.3114. Min Act: -0.0001

Data Index: 1508505 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.3865. Min Act: -0.0001

Data Index: 1003075 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.8605. Min Act: -0.0001

Data Index: 1550022 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.8354. Min Act: -0.0001

Data Index: 250892 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.8324. Min Act: -0.0001

Data Index: 1340120 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4334. Min Act: -0.0001

Data Index: 851086 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.6456. Min Act: -0.0001

Data Index: 1348665 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4880. Min Act: -0.0001

Data Index: 668418 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4920. Min Act: -0.0001

Data Index: 401827 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.6081. Min Act: -0.0001

Data Index: 1506920 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.7341. Min Act: -0.0001

Data Index: 1572304 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.5837. Min Act: -0.0001

Data Index: 1449793 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4551. Min Act: -0.0001

Data Index: 1090115 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4037. Min Act: -0.0001

Data Index: 939334 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4935. Min Act: -0.0001

Data Index: 1123814 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.2694. Min Act: -0.0001

Data Index: 692098 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4372. Min Act: -0.0001

Data Index: 1340419 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 3.5229. Min Range: -3.5229

Max Act: 2.4365. Min Act: -0.0001

Data Index: 842518 (C4 (Web Text))

Max Activating Token Index: 183