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

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

Neuron 2794 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5744. Min Act: -0.0001

Data Index: 1292375 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5460. Min Act: -0.0001

Data Index: 121095 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5401. Min Act: -0.0001

Data Index: 510019 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1018155 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5489. Min Act: -0.0001

Data Index: 323732 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5291. Min Act: -0.0001

Data Index: 971723 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5227. Min Act: -0.0001

Data Index: 96892 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5028. Min Act: -0.0001

Data Index: 1296301 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5124. Min Act: -0.0001

Data Index: 572112 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5216. Min Act: -0.0001

Data Index: 787754 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4897. Min Act: -0.0001

Data Index: 641107 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4721. Min Act: -0.0001

Data Index: 641766 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4987. Min Act: -0.0001

Data Index: 555627 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4768. Min Act: -0.0001

Data Index: 483953 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5065. Min Act: -0.0001

Data Index: 364154 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4867. Min Act: -0.0001

Data Index: 340410 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4622. Min Act: -0.0001

Data Index: 604702 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4870. Min Act: -0.0001

Data Index: 791689 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4576. Min Act: -0.0001

Data Index: 274093 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4375. Min Act: -0.0001

Data Index: 549251 (C4 (Web Text))

Max Activating Token Index: 773