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

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

Neuron 466 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: 4.2140. Min Range: -4.2140

Max Act: 4.2140. Min Act: -0.0000

Data Index: 1448195 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 4.2140. Min Range: -4.2140

Max Act: 4.1081. Min Act: -0.0000

Data Index: 1370389 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.7677. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.6475. Min Act: -0.0000

Data Index: 1636670 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.4587. Min Act: -0.0000

Data Index: 1410146 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.5585. Min Act: -0.0001

Data Index: 1451748 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.4839. Min Act: -0.0000

Data Index: 1495946 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1486696 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.3321. Min Act: -0.0000

Data Index: 1603997 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.2238. Min Act: -0.0000

Data Index: 579835 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.5075. Min Act: -0.0000

Data Index: 1572642 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.6720. Min Act: -0.0000

Data Index: 1464116 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.9377. Min Act: -0.0001

Data Index: 1466437 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.4609. Min Act: -0.0000

Data Index: 1461096 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.4480. Min Act: -0.0000

Data Index: 1627061 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.3065. Min Act: -0.0001

Data Index: 1445993 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.1463. Min Act: -0.0000

Data Index: 1585336 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.2502. Min Act: -0.0000

Data Index: 1646123 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 4.2140. Min Range: -4.2140

Max Act: 3.6689. Min Act: -0.0000

Data Index: 1469274 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 4.2140. Min Range: -4.2140

Max Act: 2.8827. Min Act: -0.0000

Data Index: 1471683 (Python Code)

Max Activating Token Index: 901