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

Dataset: The Pile

Neuron 1483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6942. Min Act: -0.0000

Data Index: 875853 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6504. Min Act: -0.0000

Data Index: 175233 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1655022 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4912. Min Act: -0.0000

Data Index: 174105 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4987. Min Act: -0.0000

Data Index: 151254 (The Pile)

Max Activating Token Index: 398

Text #5

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4351. Min Act: -0.0000

Data Index: 447868 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1097524 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1484039 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4371. Min Act: -0.0000

Data Index: 991420 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1795077 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1968438 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1269272 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1358663 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3894. Min Act: -0.0000

Data Index: 961435 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4234. Min Act: -0.0000

Data Index: 354776 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1005284 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1734095 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1489438 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3880. Min Act: -0.0000

Data Index: 694811 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3983. Min Act: -0.0000

Data Index: 813110 (The Pile)

Max Activating Token Index: 404