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

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

Neuron 1061 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: 1.1566. Min Range: -1.1566

Max Act: 1.1566. Min Act: -0.0000

Data Index: 854128 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.5595. Min Act: -0.0000

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1287949 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.3672. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2593. Min Act: -0.0000

Data Index: 892630 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2529. Min Act: -0.0000

Data Index: 901577 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.3061. Min Act: -0.0000

Data Index: 766923 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.3022. Min Act: -0.0000

Data Index: 499962 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1417301 (Python Code)

Max Activating Token Index: 673

Text #11

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2316. Min Act: -0.0000

Data Index: 851659 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.1821. Min Act: -0.0000

Data Index: 830141 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2379. Min Act: -0.0000

Data Index: 53940 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2030. Min Act: -0.0000

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2164. Min Act: -0.0000

Data Index: 798285 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1586973 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2130. Min Act: -0.0000

Data Index: 203806 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2092. Min Act: -0.0000

Data Index: 615902 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1080775 (C4 (Web Text))

Max Activating Token Index: 60