Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4873 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9802. Min Act: -0.0001

Data Index: 1244717 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1202511 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1362728 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1137156 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8212. Min Act: -0.0000

Data Index: 7481 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7703. Min Act: -0.0000

Data Index: 779113 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8896. Min Act: -0.0001

Data Index: 109157 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1461896 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1636226 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1335175 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7161. Min Act: -0.0000

Data Index: 918719 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7278. Min Act: -0.0000

Data Index: 507163 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7051. Min Act: -0.0001

Data Index: 681940 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6561. Min Act: -0.0000

Data Index: 695897 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6975. Min Act: -0.0000

Data Index: 824535 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6529. Min Act: -0.0000

Data Index: 64580 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6526. Min Act: -0.0001

Data Index: 938136 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1378581 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6924. Min Act: -0.0000

Data Index: 693202 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7758. Min Act: -0.0000

Data Index: 210427 (C4 (Web Text))

Max Activating Token Index: 366