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

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

Neuron 73 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3974. Min Range: -3.3974

Max Act: 3.3974. Min Act: -0.0000

Data Index: 2820 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.8164. Min Act: -0.0000

Data Index: 531132 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.9338. Min Act: -0.0000

Data Index: 99831 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7470. Min Act: -0.0000

Data Index: 412679 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.8521. Min Act: -0.0000

Data Index: 243437 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.8154. Min Act: -0.0000

Data Index: 70891 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7042. Min Act: -0.0000

Data Index: 626944 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.6599. Min Act: -0.0000

Data Index: 1036309 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7980. Min Act: -0.0000

Data Index: 312049 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.8013. Min Act: -0.0000

Data Index: 1359778 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.9091. Min Act: -0.0000

Data Index: 1339870 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7735. Min Act: -0.0000

Data Index: 152720 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7847. Min Act: -0.0000

Data Index: 1351609 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7783. Min Act: -0.0000

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7507. Min Act: -0.0000

Data Index: 1153588 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7750. Min Act: -0.0000

Data Index: 643671 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.9120. Min Act: -0.0000

Data Index: 479404 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7423. Min Act: -0.0000

Data Index: 717134 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.7381. Min Act: -0.0000

Data Index: 1030736 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.3974. Min Range: -3.3974

Max Act: 2.5701. Min Act: -0.0000

Data Index: 165693 (C4 (Web Text))

Max Activating Token Index: 169