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

Dataset: The Pile

Neuron 3057 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: 0.7969. Min Range: -0.7969

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1037051 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6657. Min Act: -0.0000

Data Index: 223411 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5911. Min Act: -0.0000

Data Index: 372695 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5687. Min Act: -0.0000

Data Index: 866182 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5197. Min Act: -0.0000

Data Index: 981763 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1123251 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1913237 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1416432 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4516. Min Act: -0.0000

Data Index: 84335 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1132912 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1557990 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4390. Min Act: -0.0000

Data Index: 876791 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4624. Min Act: -0.0000

Data Index: 539146 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1862184 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1464849 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1665767 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4519. Min Act: -0.0000

Data Index: 303268 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1792713 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1934596 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1537361 (The Pile)

Max Activating Token Index: 158