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

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

Neuron 4265 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: 3.5060. Min Range: -3.5060

Max Act: 3.5060. Min Act: -0.0000

Data Index: 52025 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.7620. Min Act: -0.0000

Data Index: 80418 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.4002. Min Act: -0.0000

Data Index: 103792 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.3172. Min Act: -0.0000

Data Index: 1163214 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.1911. Min Act: -0.0000

Data Index: 308532 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.1317. Min Act: -0.0000

Data Index: 1598342 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.1206. Min Act: -0.0000

Data Index: 1195570 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.1026. Min Act: -0.0000

Data Index: 82307 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.1278. Min Act: -0.0000

Data Index: 659581 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 3.5060. Min Range: -3.5060

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1220547 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9250. Min Act: -0.0000

Data Index: 1224260 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.8719. Min Act: -0.0000

Data Index: 870456 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9837. Min Act: -0.0000

Data Index: 1381793 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1246287 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9508. Min Act: -0.0000

Data Index: 1436487 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9491. Min Act: -0.0000

Data Index: 940680 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.8369. Min Act: -0.0000

Data Index: 1652297 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.8670. Min Act: -0.0000

Data Index: 1430902 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.9176. Min Act: -0.0000

Data Index: 1610668 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 3.5060. Min Range: -3.5060

Max Act: 1.7442. Min Act: -0.0001

Data Index: 1621938 (Python Code)

Max Activating Token Index: 274