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

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

Neuron 3145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1198. Min Range: -1.1198

Max Act: 1.1198. Min Act: -0.0001

Data Index: 888725 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.9443. Min Act: -0.0001

Data Index: 184964 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.1198. Min Range: -1.1198

Max Act: 1.0516. Min Act: -0.0001

Data Index: 680907 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.9505. Min Act: -0.0001

Data Index: 37124 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.9057. Min Act: -0.0001

Data Index: 55196 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.9851. Min Act: -0.0001

Data Index: 890001 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8919. Min Act: -0.0001

Data Index: 1202652 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.9054. Min Act: -0.0001

Data Index: 778038 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8784. Min Act: -0.0001

Data Index: 1274358 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8994. Min Act: -0.0001

Data Index: 820180 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8625. Min Act: -0.0001

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8494. Min Act: -0.0001

Data Index: 372943 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8499. Min Act: -0.0001

Data Index: 741153 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8453. Min Act: -0.0001

Data Index: 84065 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8280. Min Act: -0.0001

Data Index: 574482 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8311. Min Act: -0.0001

Data Index: 164440 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8768. Min Act: -0.0001

Data Index: 482334 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7497. Min Act: -0.0001

Data Index: 319245 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8428. Min Act: -0.0001

Data Index: 869316 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1248545 (C4 (Web Text))

Max Activating Token Index: 624