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

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

Neuron 2668 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2789. Min Act: 0.0000

Data Index: 1186336 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2944. Min Act: -0.0000

Data Index: 617613 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2827. Min Act: -0.0000

Data Index: 400150 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2687. Min Act: -0.0000

Data Index: 793766 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2572. Min Act: -0.0000

Data Index: 500880 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1253818 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2523. Min Act: -0.0000

Data Index: 362349 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2432. Min Act: -0.0000

Data Index: 565116 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2374. Min Act: -0.0000

Data Index: 228111 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2356. Min Act: -0.0000

Data Index: 763543 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2284. Min Act: -0.0000

Data Index: 648698 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1143061 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2328. Min Act: -0.0000

Data Index: 957115 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2374. Min Act: -0.0000

Data Index: 559667 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2296. Min Act: -0.0000

Data Index: 138306 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1112619 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2263. Min Act: 0.0000

Data Index: 742095 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1306011 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2253. Min Act: -0.0000

Data Index: 762183 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2271. Min Act: -0.0000

Data Index: 274103 (C4 (Web Text))

Max Activating Token Index: 198