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

Dataset: The Pile

Neuron 817 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1535177 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8588. Min Act: -0.0000

Data Index: 959666 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1188050 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7513. Min Act: -0.0000

Data Index: 244215 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1876122 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7442. Min Act: -0.0000

Data Index: 274277 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1667716 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1650301 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1151569 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1865906 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7126. Min Act: -0.0000

Data Index: 805826 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1424095 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6906. Min Act: -0.0000

Data Index: 563216 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1993464 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1218497 (The Pile)

Max Activating Token Index: 412

Text #15

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7315. Min Act: -0.0000

Data Index: 520371 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7066. Min Act: -0.0000

Data Index: 354005 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7048. Min Act: -0.0000

Data Index: 985058 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1293962 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1855363 (The Pile)

Max Activating Token Index: 489