Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1686818 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1790299 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1410189 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7952. Min Act: -0.0000

Data Index: 709893 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7373. Min Act: -0.0000

Data Index: 75663 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7382. Min Act: -0.0000

Data Index: 924716 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1708118 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1447536 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7335. Min Act: -0.0000

Data Index: 322787 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1744013 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6727. Min Act: -0.0000

Data Index: 980589 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6652. Min Act: -0.0000

Data Index: 559151 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1110989 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6690. Min Act: -0.0000

Data Index: 128905 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1087177 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6660. Min Act: -0.0000

Data Index: 146995 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1047598 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1036568 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1059522 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.6232. Min Act: -0.0000

Data Index: 400838 (The Pile)

Max Activating Token Index: 574