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

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

Neuron 3121 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.3063. Min Act: -0.0000

Data Index: 965827 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2771. Min Act: -0.0001

Data Index: 670829 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1245776 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2548. Min Act: -0.0000

Data Index: 32375 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2407. Min Act: -0.0000

Data Index: 696026 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2391. Min Act: -0.0001

Data Index: 437354 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2460. Min Act: -0.0000

Data Index: 707717 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1249987 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2338. Min Act: -0.0000

Data Index: 558192 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2322. Min Act: -0.0001

Data Index: 858491 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1490 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2322. Min Act: -0.0000

Data Index: 431222 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2303. Min Act: -0.0001

Data Index: 1327208 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1209302 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2058. Min Act: -0.0001

Data Index: 1085705 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2116. Min Act: -0.0001

Data Index: 986510 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1341262 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2224. Min Act: -0.0001

Data Index: 969870 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1331225 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2128. Min Act: -0.0000

Data Index: 398935 (C4 (Web Text))

Max Activating Token Index: 207