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

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

Neuron 2980 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: 1.7937. Min Range: -1.7937

Max Act: 1.7232. Min Act: -0.0001

Data Index: 722991 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.7937. Min Act: -0.0001

Data Index: 162455 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.6053. Min Act: -0.0001

Data Index: 1327944 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.6319. Min Act: -0.0001

Data Index: 847217 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.7407. Min Act: -0.0000

Data Index: 177954 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.5433. Min Act: -0.0001

Data Index: 1220514 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.5419. Min Act: -0.0001

Data Index: 737200 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.6063. Min Act: -0.0001

Data Index: 1046415 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.5675. Min Act: -0.0001

Data Index: 1067085 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.4229. Min Act: -0.0000

Data Index: 92471 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.3221. Min Act: -0.0001

Data Index: 1086612 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.3866. Min Act: -0.0001

Data Index: 406106 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.2938. Min Act: -0.0001

Data Index: 1090591 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.3268. Min Act: -0.0001

Data Index: 957971 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.3931. Min Act: -0.0001

Data Index: 384873 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.2094. Min Act: -0.0001

Data Index: 351460 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.1626. Min Act: -0.0001

Data Index: 1155286 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1134474 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1186456 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.7937. Min Range: -1.7937

Max Act: 1.5062. Min Act: -0.0001

Data Index: 567582 (C4 (Web Text))

Max Activating Token Index: 296