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

Dataset: The Pile

Neuron 4310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7576. Min Range: -3.7576

Max Act: 3.7576. Min Act: -0.0000

Data Index: 1244325 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.9791. Min Act: -0.0000

Data Index: 443954 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.9537. Min Act: -0.0000

Data Index: 325651 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.8047. Min Act: -0.0000

Data Index: 1031389 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 3.7576. Min Range: -3.7576

Max Act: 3.0505. Min Act: -0.0000

Data Index: 843575 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 3.7576. Min Range: -3.7576

Max Act: 3.2622. Min Act: -0.0000

Data Index: 265416 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.9042. Min Act: -0.0000

Data Index: 374552 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.9005. Min Act: -0.0000

Data Index: 596246 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.7079. Min Act: -0.0000

Data Index: 236199 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.6846. Min Act: -0.0000

Data Index: 527647 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5428. Min Act: -0.0000

Data Index: 898029 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.7697. Min Act: -0.0000

Data Index: 326127 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5174. Min Act: -0.0000

Data Index: 1265202 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1756622 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.8802. Min Act: -0.0000

Data Index: 1311445 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5638. Min Act: -0.0000

Data Index: 965697 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5440. Min Act: -0.0000

Data Index: 782490 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.4077. Min Act: -0.0000

Data Index: 227799 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.5169. Min Act: -0.0000

Data Index: 1189528 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 3.7576. Min Range: -3.7576

Max Act: 2.4957. Min Act: -0.0000

Data Index: 1207129 (The Pile)

Max Activating Token Index: 86