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

Dataset: The Pile

Neuron 55 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.9483. Min Act: -0.0000

Data Index: 452890 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1247221 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1885552 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7721. Min Act: -0.0000

Data Index: 432736 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7924. Min Act: 0.0000

Data Index: 945335 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1995762 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1532950 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1683573 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6890. Min Act: -0.0000

Data Index: 657454 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1921257 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1462488 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1679145 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1475185 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1191262 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1213072 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1770077 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6928. Min Act: -0.0000

Data Index: 39053 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6612. Min Act: -0.0000

Data Index: 393716 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6650. Min Act: 0.0000

Data Index: 1551132 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1321920 (The Pile)

Max Activating Token Index: 515