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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4965. Min Range: -2.4965

Max Act: 2.4965. Min Act: -0.0000

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 2.4965. Min Range: -2.4965

Max Act: 2.0450. Min Act: -0.0000

Data Index: 847986 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.9817. Min Act: -0.0000

Data Index: 721110 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.9300. Min Act: -0.0000

Data Index: 713024 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.9138. Min Act: -0.0000

Data Index: 342605 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1176081 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1046006 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8609. Min Act: -0.0000

Data Index: 660936 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8235. Min Act: -0.0000

Data Index: 787834 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.9286. Min Act: -0.0000

Data Index: 895828 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8881. Min Act: -0.0000

Data Index: 22349 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8197. Min Act: -0.0000

Data Index: 780330 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8664. Min Act: -0.0000

Data Index: 545609 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.7997. Min Act: -0.0000

Data Index: 276747 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1204001 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8402. Min Act: -0.0000

Data Index: 450643 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8134. Min Act: -0.0000

Data Index: 1139945 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8048. Min Act: -0.0000

Data Index: 539090 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.7548. Min Act: -0.0000

Data Index: 877291 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 2.4965. Min Range: -2.4965

Max Act: 1.8065. Min Act: -0.0000

Data Index: 1009691 (C4 (Web Text))

Max Activating Token Index: 319