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

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

Neuron 5701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1128187 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4837. Min Act: -0.0000

Data Index: 116561 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3983. Min Act: -0.0000

Data Index: 425841 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1018955 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3684. Min Act: -0.0000

Data Index: 598496 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3713. Min Act: -0.0000

Data Index: 186736 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3728. Min Act: -0.0000

Data Index: 932055 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1050699 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3608. Min Act: -0.0000

Data Index: 289376 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3601. Min Act: -0.0000

Data Index: 334567 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3569. Min Act: -0.0000

Data Index: 733812 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3540. Min Act: -0.0000

Data Index: 245979 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3365. Min Act: -0.0000

Data Index: 622774 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3278. Min Act: -0.0000

Data Index: 185615 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3253. Min Act: -0.0000

Data Index: 996208 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3271. Min Act: -0.0000

Data Index: 115513 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1236256 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3178. Min Act: -0.0000

Data Index: 252120 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3231. Min Act: -0.0000

Data Index: 256381 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3257. Min Act: -0.0000

Data Index: 550144 (C4 (Web Text))

Max Activating Token Index: 1017