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

Dataset: The Pile

Neuron 2835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0350. Min Range: -1.0350

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1080643 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9259. Min Act: -0.0000

Data Index: 556169 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1391401 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9062. Min Act: -0.0000

Data Index: 317503 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1247400 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1088224 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1562852 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9522. Min Act: -0.0000

Data Index: 697792 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1182640 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9424. Min Act: -0.0000

Data Index: 32580 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1191221 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1773498 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9083. Min Act: -0.0000

Data Index: 280241 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1175246 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1281119 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8369. Min Act: -0.0000

Data Index: 864753 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8289. Min Act: -0.0000

Data Index: 488906 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1337963 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1668457 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 1.0350. Min Range: -1.0350

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1913489 (The Pile)

Max Activating Token Index: 968