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

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

Neuron 282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.6076. Min Act: -0.0001

Data Index: 700349 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5311. Min Act: -0.0001

Data Index: 1638145 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5443. Min Act: -0.0001

Data Index: 712136 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4924. Min Act: -0.0001

Data Index: 83460 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4850. Min Act: -0.0001

Data Index: 167846 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5000. Min Act: -0.0001

Data Index: 119368 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5142. Min Act: -0.0001

Data Index: 674750 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1157183 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5039. Min Act: -0.0001

Data Index: 505847 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4997. Min Act: -0.0001

Data Index: 798640 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4968. Min Act: -0.0001

Data Index: 1601222 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4935. Min Act: -0.0001

Data Index: 597976 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4761. Min Act: -0.0001

Data Index: 346736 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.5087. Min Act: -0.0001

Data Index: 827357 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4794. Min Act: -0.0001

Data Index: 417472 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4765. Min Act: -0.0001

Data Index: 99755 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4917. Min Act: -0.0001

Data Index: 603003 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1297017 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4656. Min Act: -0.0001

Data Index: 101719 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.6076. Min Range: -0.6076

Max Act: 0.4777. Min Act: -0.0001

Data Index: 813730 (C4 (Web Text))

Max Activating Token Index: 164