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

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

Neuron 3161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1216296 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1095990 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.7651. Min Act: -0.0000

Data Index: 692015 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.6240. Min Act: -0.0000

Data Index: 935036 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.6764. Min Act: -0.0000

Data Index: 723656 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.6120. Min Act: -0.0000

Data Index: 332423 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1131565 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5993. Min Act: -0.0000

Data Index: 523800 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5870. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5303. Min Act: -0.0000

Data Index: 96088 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5958. Min Act: -0.0000

Data Index: 309626 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5945. Min Act: -0.0000

Data Index: 820890 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4938. Min Act: -0.0000

Data Index: 716079 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1086870 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1001912 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1277221 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4832. Min Act: -0.0000

Data Index: 893893 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4405. Min Act: -0.0000

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4756. Min Act: -0.0000

Data Index: 42211 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.8199. Min Range: -1.8199

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1163212 (C4 (Web Text))

Max Activating Token Index: 508