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

Dataset: The Pile

Neuron 2784 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: 1.7330. Min Range: -1.7330

Max Act: 1.6874. Min Act: -0.0000

Data Index: 452767 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1465827 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1146259 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1073334 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5742. Min Act: -0.0000

Data Index: 1250528 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1268685 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1400909 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1544269 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3754. Min Act: -0.0000

Data Index: 898823 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1783311 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1399686 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4439. Min Act: -0.0000

Data Index: 400664 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1631783 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.4439. Min Act: -0.0000

Data Index: 218584 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1764220 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3370. Min Act: -0.0000

Data Index: 291492 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1265938 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1978554 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3709. Min Act: -0.0000

Data Index: 110201 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 1.7330. Min Range: -1.7330

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1471530 (The Pile)

Max Activating Token Index: 802