Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2777. Min Act: -0.0001

Data Index: 942944 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1201811 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2630. Min Act: -0.0001

Data Index: 88589 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2447. Min Act: -0.0001

Data Index: 9306 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2439. Min Act: -0.0001

Data Index: 59543 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2368. Min Act: -0.0000

Data Index: 31436 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2307. Min Act: -0.0000

Data Index: 66210 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1027855 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1065654 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1141122 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2311. Min Act: -0.0001

Data Index: 626393 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2149. Min Act: -0.0001

Data Index: 687618 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2260. Min Act: -0.0001

Data Index: 272847 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2185. Min Act: -0.0001

Data Index: 229692 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2156. Min Act: -0.0000

Data Index: 281245 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2193. Min Act: -0.0000

Data Index: 342498 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2125. Min Act: -0.0001

Data Index: 643078 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2106. Min Act: -0.0001

Data Index: 44030 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1108261 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1323876 (C4 (Web Text))

Max Activating Token Index: 107