Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2211 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6318. Min Act: 0.0000

Data Index: 620708 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6141. Min Act: 0.0001

Data Index: 225212 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1325392 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.6257. Min Act: 0.0000

Data Index: 590244 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5472. Min Act: 0.0000

Data Index: 84924 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5498. Min Act: 0.0001

Data Index: 1138893 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5326. Min Act: 0.0000

Data Index: 214848 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5489. Min Act: -0.0000

Data Index: 531914 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5262. Min Act: -0.0000

Data Index: 298293 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5034. Min Act: 0.0000

Data Index: 306456 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4990. Min Act: 0.0001

Data Index: 1127560 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.5331. Min Act: -0.0000

Data Index: 417384 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1088456 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1418501 (Python Code)

Max Activating Token Index: 786

Text #14

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1353344 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4670. Min Act: -0.0000

Data Index: 488846 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4749. Min Act: 0.0000

Data Index: 1082203 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4871. Min Act: 0.0000

Data Index: 209826 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4531. Min Act: 0.0000

Data Index: 776098 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.6318. Min Range: -0.6318

Max Act: 0.4861. Min Act: -0.0000

Data Index: 811959 (C4 (Web Text))

Max Activating Token Index: 343