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

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

Neuron 3939 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0693. Min Act: -0.0001

Data Index: 797481 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0075. Min Act: -0.0001

Data Index: 1028779 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8049. Min Act: -0.0001

Data Index: 326360 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8293. Min Act: -0.0001

Data Index: 175186 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8975. Min Act: -0.0001

Data Index: 962340 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8727. Min Act: -0.0001

Data Index: 1079332 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7847. Min Act: -0.0001

Data Index: 1091412 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7348. Min Act: -0.0001

Data Index: 693478 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7870. Min Act: -0.0001

Data Index: 1083560 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7364. Min Act: -0.0001

Data Index: 420878 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7541. Min Act: -0.0001

Data Index: 96965 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1120278 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8179. Min Act: -0.0001

Data Index: 155875 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7111. Min Act: -0.0001

Data Index: 186883 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1291751 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7193. Min Act: -0.0001

Data Index: 961970 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7558. Min Act: -0.0001

Data Index: 250108 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7306. Min Act: -0.0001

Data Index: 451411 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7093. Min Act: -0.0001

Data Index: 976110 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.6813. Min Act: -0.0001

Data Index: 1249511 (C4 (Web Text))

Max Activating Token Index: 226