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

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

Neuron 1272 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1080121 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2555. Min Act: -0.0000

Data Index: 619151 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2661. Min Act: -0.0001

Data Index: 993033 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1284120 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2515. Min Act: -0.0001

Data Index: 61118 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2278. Min Act: -0.0001

Data Index: 981956 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2323. Min Act: -0.0000

Data Index: 364599 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2365. Min Act: -0.0001

Data Index: 1278008 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2197. Min Act: -0.0001

Data Index: 802094 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2175. Min Act: -0.0001

Data Index: 582004 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2164. Min Act: -0.0000

Data Index: 533164 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1026939 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2033. Min Act: -0.0000

Data Index: 92014 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1339549 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1892. Min Act: -0.0001

Data Index: 78482 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1916. Min Act: -0.0001

Data Index: 112844 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1915. Min Act: -0.0000

Data Index: 862538 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1879. Min Act: -0.0001

Data Index: 150276 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1426588 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1441987 (Python Code)

Max Activating Token Index: 692