Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 53 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5868. Min Act: -0.0001

Data Index: 714779 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5719. Min Act: -0.0001

Data Index: 193026 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5442. Min Act: -0.0001

Data Index: 226454 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5132. Min Act: -0.0001

Data Index: 350884 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5069. Min Act: -0.0001

Data Index: 655562 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4712. Min Act: -0.0001

Data Index: 713924 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4832. Min Act: -0.0001

Data Index: 626694 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4897. Min Act: -0.0001

Data Index: 967942 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4774. Min Act: -0.0001

Data Index: 728306 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4462. Min Act: -0.0001

Data Index: 246245 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4525. Min Act: -0.0001

Data Index: 344317 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.3988. Min Act: -0.0001

Data Index: 928695 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4330. Min Act: -0.0001

Data Index: 54707 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4291. Min Act: -0.0001

Data Index: 139840 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4411. Min Act: -0.0001

Data Index: 161875 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4396. Min Act: -0.0001

Data Index: 942790 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4550. Min Act: -0.0001

Data Index: 270787 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4210. Min Act: -0.0001

Data Index: 546397 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4347. Min Act: -0.0001

Data Index: 551204 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4319. Min Act: -0.0001

Data Index: 391492 (C4 (Web Text))

Max Activating Token Index: 52