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

Dataset: The Pile

Neuron 3607 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: 1.5799. Min Range: -1.5799

Max Act: 1.5799. Min Act: -0.0000

Data Index: 495309 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.5595. Min Act: -0.0000

Data Index: 521121 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3940. Min Act: -0.0000

Data Index: 720881 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1748890 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1356092 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3143. Min Act: -0.0000

Data Index: 540245 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1858912 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1761296 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3227. Min Act: -0.0000

Data Index: 275622 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2042. Min Act: -0.0000

Data Index: 545501 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1275267 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2161. Min Act: -0.0000

Data Index: 251015 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2210. Min Act: -0.0000

Data Index: 868334 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0850. Min Act: -0.0000

Data Index: 573072 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1425486 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1079356 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1247939 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2236. Min Act: -0.0000

Data Index: 382724 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1151985 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1783. Min Act: -0.0000

Data Index: 116533 (The Pile)

Max Activating Token Index: 36