Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1642 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.5146. Min Act: -0.0001

Data Index: 681184 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4803. Min Act: -0.0001

Data Index: 345431 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4515. Min Act: -0.0001

Data Index: 877956 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4348. Min Act: -0.0001

Data Index: 739427 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4255. Min Act: -0.0001

Data Index: 251694 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4320. Min Act: -0.0001

Data Index: 737438 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4453. Min Act: -0.0001

Data Index: 145028 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1177935 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4188. Min Act: -0.0001

Data Index: 100945 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4011. Min Act: -0.0001

Data Index: 307701 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3956. Min Act: -0.0001

Data Index: 67129 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4248. Min Act: -0.0001

Data Index: 103256 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1033205 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4064. Min Act: -0.0001

Data Index: 1251974 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3851. Min Act: -0.0001

Data Index: 1320360 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1217663 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1309239 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3935. Min Act: -0.0001

Data Index: 65765 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3939. Min Act: -0.0001

Data Index: 557883 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1281578 (C4 (Web Text))

Max Activating Token Index: 116