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

Dataset: The Pile

Neuron 3956 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.7442. Min Act: -0.0000

Data Index: 461550 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 5.0225. Min Range: -5.0225

Max Act: 5.0225. Min Act: -0.0000

Data Index: 612546 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.7770. Min Act: -0.0000

Data Index: 1907122 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.7581. Min Act: -0.0000

Data Index: 620794 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.7339. Min Act: -0.0000

Data Index: 271397 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.1407. Min Act: -0.0000

Data Index: 1851903 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.5390. Min Act: -0.0000

Data Index: 1157461 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.2575. Min Act: -0.0000

Data Index: 310600 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.4068. Min Act: -0.0000

Data Index: 1221696 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.4302. Min Act: -0.0000

Data Index: 1562656 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.3839. Min Act: -0.0000

Data Index: 1018551 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 5.0225. Min Range: -5.0225

Max Act: 3.9992. Min Act: -0.0000

Data Index: 1674237 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.2279. Min Act: -0.0000

Data Index: 1489810 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.0399. Min Act: -0.0000

Data Index: 648284 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.2483. Min Act: -0.0000

Data Index: 694241 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.3906. Min Act: -0.0000

Data Index: 1476745 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.0597. Min Act: -0.0000

Data Index: 872822 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.1810. Min Act: -0.0000

Data Index: 917326 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.1952. Min Act: -0.0000

Data Index: 524789 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 5.0225. Min Range: -5.0225

Max Act: 4.2027. Min Act: -0.0000

Data Index: 113854 (The Pile)

Max Activating Token Index: 452