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

Dataset: The Pile

Neuron 276 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: 0.8339. Min Range: -0.8339

Max Act: 0.8339. Min Act: -0.0000

Data Index: 532082 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1036854 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1396290 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1023569 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5441. Min Act: -0.0000

Data Index: 808250 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1423962 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5559. Min Act: -0.0000

Data Index: 738369 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4929. Min Act: -0.0000

Data Index: 671627 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4971. Min Act: -0.0000

Data Index: 661116 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4402. Min Act: -0.0000

Data Index: 448740 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4944. Min Act: -0.0000

Data Index: 886153 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1359362 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4082. Min Act: -0.0000

Data Index: 187385 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1768317 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4697. Min Act: -0.0000

Data Index: 935169 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.3897. Min Act: -0.0000

Data Index: 293427 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1957714 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1657365 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1238091 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.3964. Min Act: -0.0000

Data Index: 364480 (The Pile)

Max Activating Token Index: 86