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

Dataset: The Pile

Neuron 1489 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4348. Min Range: -5.4348

Max Act: 5.4348. Min Act: -0.0000

Data Index: 1654147 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 5.4348. Min Range: -5.4348

Max Act: 5.0833. Min Act: -0.0000

Data Index: 1980205 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 5.4348. Min Range: -5.4348

Max Act: 5.4025. Min Act: -0.0000

Data Index: 323460 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 5.4348. Min Range: -5.4348

Max Act: 5.1505. Min Act: -0.0000

Data Index: 1833921 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.9578. Min Act: -0.0000

Data Index: 196019 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.5155. Min Act: -0.0000

Data Index: 943633 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 5.4348. Min Range: -5.4348

Max Act: 5.0179. Min Act: -0.0000

Data Index: 1699547 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.8118. Min Act: -0.0000

Data Index: 867336 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.7456. Min Act: -0.0000

Data Index: 1951096 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.7206. Min Act: -0.0000

Data Index: 1001031 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.7199. Min Act: -0.0000

Data Index: 1070544 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.5905. Min Act: -0.0000

Data Index: 1572005 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.5757. Min Act: -0.0000

Data Index: 1893209 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.4942. Min Act: -0.0000

Data Index: 918607 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.4727. Min Act: -0.0000

Data Index: 316416 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.2772. Min Act: -0.0000

Data Index: 623265 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.1740. Min Act: -0.0000

Data Index: 1990210 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.3198. Min Act: -0.0000

Data Index: 285790 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 5.4348. Min Range: -5.4348

Max Act: 3.9825. Min Act: -0.0000

Data Index: 741928 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 5.4348. Min Range: -5.4348

Max Act: 4.1313. Min Act: -0.0000

Data Index: 35185 (The Pile)

Max Activating Token Index: 225