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

Dataset: The Pile

Neuron 3110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3927. Min Act: -0.0000

Data Index: 862827 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1816059 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3206. Min Act: -0.0000

Data Index: 731946 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2951. Min Act: -0.0000

Data Index: 190672 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2996. Min Act: -0.0000

Data Index: 104704 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2796. Min Act: -0.0000

Data Index: 260091 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1960436 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1099993 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2770. Min Act: -0.0000

Data Index: 837162 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1529784 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1388884 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2620. Min Act: -0.0000

Data Index: 471965 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1410966 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2625. Min Act: -0.0000

Data Index: 53401 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2412. Min Act: -0.0000

Data Index: 601162 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1206716 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1319558 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2367. Min Act: -0.0000

Data Index: 650567 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1924738 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2179. Min Act: -0.0000

Data Index: 207937 (The Pile)

Max Activating Token Index: 777