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

Dataset: The Pile

Neuron 634 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: 1.0204. Min Range: -1.0204

Max Act: 1.0009. Min Act: -0.0000

Data Index: 551042 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1105070 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.0204. Min Range: -1.0204

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1779747 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8556. Min Act: -0.0000

Data Index: 868717 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1910429 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8588. Min Act: -0.0000

Data Index: 772301 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1602045 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8578. Min Act: -0.0000

Data Index: 685290 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8284. Min Act: -0.0000

Data Index: 734711 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1153965 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1102040 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1476524 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.7201. Min Act: -0.0000

Data Index: 837741 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8365. Min Act: -0.0000

Data Index: 627799 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8117. Min Act: -0.0000

Data Index: 901551 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8349. Min Act: -0.0000

Data Index: 415338 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1352007 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1342317 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1900624 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 1.0204. Min Range: -1.0204

Max Act: 0.8366. Min Act: -0.0000

Data Index: 375231 (The Pile)

Max Activating Token Index: 64