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

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

Neuron 2158 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.3488. Min Act: -0.0000

Data Index: 1146082 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.4748. Min Act: -0.0000

Data Index: 1556687 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.4712. Min Act: -0.0000

Data Index: 600377 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.4050. Min Act: -0.0000

Data Index: 698713 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9606. Min Act: -0.0000

Data Index: 1330987 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.8446. Min Act: -0.0000

Data Index: 338825 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.8044. Min Act: -0.0000

Data Index: 184065 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.7756. Min Act: -0.0000

Data Index: 663379 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.5749. Min Act: -0.0000

Data Index: 1217820 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.7515. Min Act: -0.0000

Data Index: 156645 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.7133. Min Act: -0.0000

Data Index: 744026 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.5219. Min Act: -0.0000

Data Index: 1348938 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.6983. Min Act: -0.0000

Data Index: 805529 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.8462. Min Act: -0.0000

Data Index: 1261514 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.6574. Min Act: -0.0000

Data Index: 26627 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.6296. Min Act: -0.0000

Data Index: 760789 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.6228. Min Act: -0.0000

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.6126. Min Act: -0.0000

Data Index: 1179166 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.4370. Min Act: -0.0000

Data Index: 1170160 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.4153. Min Act: -0.0000

Data Index: 1261984 (C4 (Web Text))

Max Activating Token Index: 801