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

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

Neuron 4341 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: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0000

Data Index: 926988 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1308219 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2625. Min Act: -0.0000

Data Index: 684249 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2585. Min Act: -0.0000

Data Index: 5288 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2616. Min Act: -0.0000

Data Index: 630389 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2494. Min Act: -0.0000

Data Index: 603183 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2451. Min Act: -0.0000

Data Index: 415988 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2393. Min Act: -0.0000

Data Index: 54836 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2298. Min Act: -0.0000

Data Index: 180533 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1076598 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2232. Min Act: -0.0000

Data Index: 355786 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2160. Min Act: -0.0000

Data Index: 932946 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1792. Min Act: -0.0000

Data Index: 684471 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1157468 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1138224 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2081. Min Act: -0.0000

Data Index: 446623 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1270584 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2012. Min Act: -0.0000

Data Index: 449270 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2032. Min Act: -0.0000

Data Index: 901177 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2088. Min Act: -0.0000

Data Index: 182110 (C4 (Web Text))

Max Activating Token Index: 359