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

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

Neuron 2382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2465. Min Range: -4.2465

Max Act: 4.2465. Min Act: -0.0000

Data Index: 932968 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.2465. Min Range: -4.2465

Max Act: 3.7159. Min Act: -0.0000

Data Index: 195784 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 4.2465. Min Range: -4.2465

Max Act: 3.2568. Min Act: -0.0000

Data Index: 943523 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 4.2465. Min Range: -4.2465

Max Act: 3.3060. Min Act: -0.0000

Data Index: 320849 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.8993. Min Act: -0.0000

Data Index: 1140891 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.7909. Min Act: -0.0000

Data Index: 22489 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.9162. Min Act: -0.0000

Data Index: 145911 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.8993. Min Act: -0.0000

Data Index: 1011265 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.8928. Min Act: -0.0000

Data Index: 554163 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.7392. Min Act: -0.0000

Data Index: 29781 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.6107. Min Act: -0.0000

Data Index: 226610 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.7246. Min Act: -0.0000

Data Index: 388935 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.9155. Min Act: -0.0000

Data Index: 856816 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.5865. Min Act: -0.0000

Data Index: 108778 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1133701 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1048022 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.6651. Min Act: -0.0000

Data Index: 1331231 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.5163. Min Act: -0.0000

Data Index: 1148713 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.3994. Min Act: -0.0000

Data Index: 406578 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 4.2465. Min Range: -4.2465

Max Act: 2.5173. Min Act: -0.0000

Data Index: 295073 (C4 (Web Text))

Max Activating Token Index: 775