Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 763 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3842. Min Act: -0.0001

Data Index: 776835 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.7499. Min Act: -0.0001

Data Index: 441106 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1018128 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1049555 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.6653. Min Act: -0.0001

Data Index: 432734 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1056015 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1160717 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5995. Min Act: -0.0001

Data Index: 1008783 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.6413. Min Act: -0.0001

Data Index: 391749 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1270157 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5188. Min Act: -0.0001

Data Index: 388305 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.4921. Min Act: -0.0001

Data Index: 562551 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.6090. Min Act: -0.0001

Data Index: 616894 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.4794. Min Act: -0.0001

Data Index: 228421 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.4926. Min Act: -0.0001

Data Index: 926748 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5056. Min Act: -0.0001

Data Index: 115273 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1105590 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.5335. Min Act: -0.0001

Data Index: 321194 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1107713 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.4959. Min Act: -0.0001

Data Index: 164415 (C4 (Web Text))

Max Activating Token Index: 466