Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1065 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0000

Data Index: 254691 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1110243 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8209. Min Act: -0.0000

Data Index: 727095 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7788. Min Act: 0.0001

Data Index: 1215912 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1100929 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1083883 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1000486 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1277429 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6802. Min Act: -0.0000

Data Index: 552318 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6978. Min Act: -0.0000

Data Index: 2941 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6782. Min Act: -0.0000

Data Index: 727337 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6933. Min Act: -0.0000

Data Index: 437984 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6977. Min Act: -0.0000

Data Index: 600596 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6704. Min Act: -0.0000

Data Index: 831786 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1257597 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6648. Min Act: -0.0000

Data Index: 856293 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7028. Min Act: -0.0000

Data Index: 849252 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6040. Min Act: -0.0000

Data Index: 76181 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6556. Min Act: -0.0000

Data Index: 3594 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6500. Min Act: -0.0000

Data Index: 981537 (C4 (Web Text))

Max Activating Token Index: 819