Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3764 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1751925 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.1018. Min Act: -0.0000

Data Index: 971843 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1990280 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1052909 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.0272. Min Act: -0.0000

Data Index: 36202 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.2190. Min Range: -1.2190

Max Act: 1.1914. Min Act: -0.0000

Data Index: 47177 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9868. Min Act: 0.0000

Data Index: 294243 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1092575 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1543606 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1639310 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1436090 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1788174 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8231. Min Act: -0.0000

Data Index: 986211 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7583. Min Act: -0.0000

Data Index: 817562 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1571821 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1583518 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.8566. Min Act: -0.0000

Data Index: 260454 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1161948 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7274. Min Act: -0.0000

Data Index: 333903 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.2190. Min Range: -1.2190

Max Act: 0.7276. Min Act: -0.0000

Data Index: 175180 (The Pile)

Max Activating Token Index: 539