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

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

Neuron 3757 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6025. Min Act: -0.0000

Data Index: 1287017 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6953. Min Act: -0.0000

Data Index: 29817 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1211265 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6122. Min Act: -0.0000

Data Index: 227223 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.5223. Min Act: -0.0000

Data Index: 124409 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4962. Min Act: -0.0000

Data Index: 573392 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.5319. Min Act: -0.0000

Data Index: 869943 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1145561 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4096. Min Act: -0.0000

Data Index: 553764 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4525. Min Act: -0.0000

Data Index: 881671 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4509. Min Act: -0.0000

Data Index: 44149 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1262288 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1128547 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.3647. Min Act: -0.0000

Data Index: 157950 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4047. Min Act: -0.0000

Data Index: 50841 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4110. Min Act: -0.0000

Data Index: 20261 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1227250 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2912. Min Act: -0.0000

Data Index: 92602 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.3171. Min Act: -0.0000

Data Index: 698405 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2802. Min Act: -0.0000

Data Index: 976062 (C4 (Web Text))

Max Activating Token Index: 868