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

Dataset: The Pile

Neuron 3015 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: 0.4974. Min Range: -0.4974

Max Act: 0.4974. Min Act: -0.0000

Data Index: 561143 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1236193 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3902. Min Act: -0.0000

Data Index: 613453 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3875. Min Act: -0.0000

Data Index: 397322 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1899146 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1004211 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1345262 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1670283 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3397. Min Act: -0.0000

Data Index: 280395 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3317. Min Act: -0.0000

Data Index: 605690 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3279. Min Act: -0.0000

Data Index: 201800 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1864813 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1351361 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3271. Min Act: -0.0000

Data Index: 328837 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1400853 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1218800 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1152067 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.2858. Min Act: -0.0000

Data Index: 31055 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.2937. Min Act: -0.0000

Data Index: 132494 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1140807 (The Pile)

Max Activating Token Index: 985