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

Dataset: The Pile

Neuron 2083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9340. Min Act: -0.0000

Data Index: 1434477 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9378. Min Act: -0.0000

Data Index: 943327 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4589. Min Act: -0.0000

Data Index: 861213 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.2882. Min Act: -0.0000

Data Index: 473572 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.0559. Min Act: -0.0000

Data Index: 1188064 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.8557. Min Act: -0.0000

Data Index: 911189 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.7885. Min Act: -0.0000

Data Index: 1236487 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.5906. Min Act: -0.0000

Data Index: 1262548 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.6880. Min Act: -0.0000

Data Index: 534115 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1160857 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.4790. Min Act: -0.0000

Data Index: 1446440 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.3079. Min Act: -0.0000

Data Index: 856863 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.3919. Min Act: -0.0000

Data Index: 774418 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.4524. Min Act: -0.0000

Data Index: 92512 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.3457. Min Act: -0.0000

Data Index: 692657 (The Pile)

Max Activating Token Index: 728

Text #15

Max Range: 3.9378. Min Range: -3.9378

Max Act: 1.9920. Min Act: -0.0000

Data Index: 817017 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.2958. Min Act: -0.0000

Data Index: 888094 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.0523. Min Act: -0.0000

Data Index: 608670 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.0586. Min Act: -0.0000

Data Index: 1378728 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 3.9378. Min Range: -3.9378

Max Act: 2.0864. Min Act: -0.0000

Data Index: 910085 (The Pile)

Max Activating Token Index: 478