Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.4540. Min Act: -0.0000

Data Index: 1467894 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.3103. Min Act: -0.0000

Data Index: 1616217 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.6076. Min Act: -0.0000

Data Index: 1631280 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1552092 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.3202. Min Act: -0.0000

Data Index: 1477493 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.1656. Min Act: 0.0000

Data Index: 1451474 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1480314 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.0876. Min Act: -0.0000

Data Index: 1432511 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.9528. Min Act: -0.0000

Data Index: 1503611 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.0832. Min Act: -0.0000

Data Index: 1425118 (Python Code)

Max Activating Token Index: 130

Text #10

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.0058. Min Act: -0.0000

Data Index: 1652120 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.8375. Min Act: -0.0000

Data Index: 1592789 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.9678. Min Act: -0.0000

Data Index: 1600938 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.8046. Min Act: -0.0000

Data Index: 1623333 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 3.6076. Min Range: -3.6076

Max Act: 3.0205. Min Act: -0.0000

Data Index: 1393861 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.7839. Min Act: -0.0000

Data Index: 1627401 (Python Code)

Max Activating Token Index: 584

Text #16

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.9342. Min Act: -0.0000

Data Index: 1369313 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.7772. Min Act: -0.0000

Data Index: 1417246 (Python Code)

Max Activating Token Index: 411

Text #18

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.9048. Min Act: -0.0000

Data Index: 1632161 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 3.6076. Min Range: -3.6076

Max Act: 2.7407. Min Act: -0.0000

Data Index: 1625689 (Python Code)

Max Activating Token Index: 611