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

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

Neuron 1343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.1298. Min Act: -0.0001

Data Index: 400614 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.1157. Min Act: -0.0001

Data Index: 715399 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0182. Min Act: -0.0001

Data Index: 112989 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0055. Min Act: -0.0001

Data Index: 994407 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0597. Min Act: -0.0001

Data Index: 178222 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9925. Min Act: -0.0001

Data Index: 518688 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.1298. Min Range: -1.1298

Max Act: 1.0080. Min Act: -0.0001

Data Index: 1244528 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9627. Min Act: -0.0001

Data Index: 1147997 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8716. Min Act: -0.0001

Data Index: 618453 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9821. Min Act: -0.0001

Data Index: 1244245 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9322. Min Act: -0.0001

Data Index: 420027 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9680. Min Act: -0.0001

Data Index: 304352 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8918. Min Act: -0.0001

Data Index: 790094 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9187. Min Act: -0.0001

Data Index: 293248 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1215047 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8343. Min Act: -0.0001

Data Index: 841667 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1255020 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9049. Min Act: -0.0001

Data Index: 317589 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1335370 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.1298. Min Range: -1.1298

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1298784 (C4 (Web Text))

Max Activating Token Index: 522