Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5741 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.5094. Min Act: -0.0001

Data Index: 855662 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.4165. Min Act: -0.0001

Data Index: 167760 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.3624. Min Act: -0.0001

Data Index: 1281493 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.2147. Min Act: -0.0001

Data Index: 548022 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.2053. Min Act: -0.0001

Data Index: 542504 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1833. Min Act: -0.0001

Data Index: 1191361 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0372. Min Act: -0.0001

Data Index: 70017 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1103520 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1685. Min Act: -0.0001

Data Index: 137575 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0286. Min Act: -0.0001

Data Index: 798994 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9915. Min Act: -0.0001

Data Index: 458686 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1620. Min Act: -0.0001

Data Index: 963278 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1680. Min Act: -0.0001

Data Index: 1051420 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.8709. Min Act: -0.0001

Data Index: 103234 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0697. Min Act: -0.0001

Data Index: 1247968 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1003953 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.5094. Min Range: -1.5094

Max Act: 1.1425. Min Act: -0.0001

Data Index: 629238 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9760. Min Act: -0.0001

Data Index: 1046707 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9152. Min Act: -0.0001

Data Index: 257361 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.5094. Min Range: -1.5094

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1343915 (C4 (Web Text))

Max Activating Token Index: 425