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

Dataset: The Pile

Neuron 2228 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: 0.8276. Min Range: -0.8276

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1006165 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1883305 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7513. Min Act: -0.0000

Data Index: 716911 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1426063 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1147084 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1846451 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1807572 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7700. Min Act: -0.0000

Data Index: 12221 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7042. Min Act: -0.0000

Data Index: 857128 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7382. Min Act: -0.0000

Data Index: 499623 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7180. Min Act: -0.0000

Data Index: 545725 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1419116 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1614823 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1451881 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6789. Min Act: -0.0000

Data Index: 819740 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1698124 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6623. Min Act: -0.0000

Data Index: 757439 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.5790. Min Act: -0.0000

Data Index: 173042 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6406. Min Act: -0.0000

Data Index: 666711 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 0.8276. Min Range: -0.8276

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1359990 (The Pile)

Max Activating Token Index: 48