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

Dataset: The Pile

Neuron 2270 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: 1.4486. Min Range: -1.4486

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1429634 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.4106. Min Act: -0.0000

Data Index: 298183 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1278807 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.3030. Min Act: -0.0001

Data Index: 1598871 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.2637. Min Act: -0.0000

Data Index: 669739 (The Pile)

Max Activating Token Index: 114

Text #5

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1457438 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1263340 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.2542. Min Act: -0.0000

Data Index: 196905 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1256224 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1651. Min Act: -0.0000

Data Index: 877132 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1091147 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1769. Min Act: -0.0000

Data Index: 697447 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1336. Min Act: -0.0000

Data Index: 30667 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1554. Min Act: -0.0000

Data Index: 485384 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.0778. Min Act: -0.0001

Data Index: 1852602 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1318. Min Act: -0.0000

Data Index: 823767 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.0557. Min Act: -0.0000

Data Index: 162536 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1383940 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1365813 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 1.4486. Min Range: -1.4486

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1092420 (The Pile)

Max Activating Token Index: 54