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

Dataset: The Pile

Neuron 2239 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1404929 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.7081. Min Act: -0.0000

Data Index: 726242 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1234083 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1627400 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3012. Min Act: -0.0000

Data Index: 823174 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3692. Min Act: -0.0000

Data Index: 761446 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3277. Min Act: -0.0000

Data Index: 846761 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3343. Min Act: -0.0000

Data Index: 30571 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3490. Min Act: -0.0000

Data Index: 891082 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1530634 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1059336 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2169. Min Act: -0.0000

Data Index: 630400 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1942604 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2267. Min Act: -0.0000

Data Index: 453536 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2253. Min Act: -0.0000

Data Index: 315802 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2686. Min Act: -0.0000

Data Index: 561826 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.1502. Min Act: -0.0000

Data Index: 559827 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2752. Min Act: -0.0000

Data Index: 508709 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1706503 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.7081. Min Range: -1.7081

Max Act: 1.2386. Min Act: -0.0000

Data Index: 434996 (The Pile)

Max Activating Token Index: 233