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

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

Neuron 2485 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: 4.1975. Min Range: -4.1975

Max Act: 4.1975. Min Act: -0.0000

Data Index: 923672 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.8679. Min Act: -0.0000

Data Index: 844168 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.8344. Min Act: -0.0000

Data Index: 441598 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.6329. Min Act: -0.0000

Data Index: 1079519 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.2905. Min Act: -0.0000

Data Index: 401094 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.8001. Min Act: -0.0000

Data Index: 611975 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3245. Min Act: -0.0000

Data Index: 363012 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3078. Min Act: -0.0000

Data Index: 696232 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.4394. Min Act: -0.0000

Data Index: 521651 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3611. Min Act: -0.0000

Data Index: 940090 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3948. Min Act: -0.0000

Data Index: 1037122 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3527. Min Act: -0.0000

Data Index: 548556 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.3259. Min Act: -0.0000

Data Index: 620658 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.1721. Min Act: -0.0000

Data Index: 981615 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.1580. Min Act: -0.0000

Data Index: 1340887 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.1682. Min Act: -0.0000

Data Index: 121518 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.2681. Min Act: -0.0000

Data Index: 560504 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.2723. Min Act: -0.0000

Data Index: 1255845 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.5641. Min Act: -0.0000

Data Index: 246423 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 4.1975. Min Range: -4.1975

Max Act: 3.2551. Min Act: -0.0000

Data Index: 431845 (C4 (Web Text))

Max Activating Token Index: 296