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

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

Neuron 3881 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.5465. Min Act: -0.0001

Data Index: 101042 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.6241. Min Act: -0.0000

Data Index: 611714 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.3862. Min Act: -0.0000

Data Index: 189247 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2959. Min Act: -0.0000

Data Index: 122945 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.3544. Min Act: -0.0001

Data Index: 621092 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2983. Min Act: -0.0000

Data Index: 617857 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1866. Min Act: -0.0001

Data Index: 1269365 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2598. Min Act: -0.0001

Data Index: 1358344 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1042654 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2392. Min Act: -0.0001

Data Index: 305103 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1265517 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2272. Min Act: -0.0000

Data Index: 471674 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1500. Min Act: -0.0000

Data Index: 387347 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1358273 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1341363 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2818. Min Act: -0.0000

Data Index: 944410 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.2695. Min Act: -0.0000

Data Index: 749462 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1834. Min Act: -0.0001

Data Index: 1226586 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.1746. Min Act: -0.0001

Data Index: 204090 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.0610. Min Act: -0.0000

Data Index: 392666 (C4 (Web Text))

Max Activating Token Index: 918