Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4663. Min Act: -0.0001

Data Index: 1099979 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4779. Min Act: -0.0001

Data Index: 724352 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.5255. Min Act: -0.0001

Data Index: 78997 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4585. Min Act: -0.0001

Data Index: 1193978 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4112. Min Act: -0.0001

Data Index: 315574 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4539. Min Act: -0.0001

Data Index: 95246 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4337. Min Act: -0.0001

Data Index: 170742 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4543. Min Act: -0.0001

Data Index: 841500 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4238. Min Act: -0.0001

Data Index: 788433 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3560. Min Act: -0.0001

Data Index: 988801 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3549. Min Act: -0.0001

Data Index: 1101240 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3477. Min Act: -0.0001

Data Index: 315318 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3891. Min Act: -0.0001

Data Index: 951366 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3822. Min Act: -0.0001

Data Index: 452890 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4267. Min Act: -0.0001

Data Index: 257999 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4133. Min Act: -0.0001

Data Index: 962082 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3192. Min Act: -0.0001

Data Index: 1169364 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3582. Min Act: -0.0001

Data Index: 543697 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3962. Min Act: -0.0001

Data Index: 1343415 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3567. Min Act: -0.0001

Data Index: 32906 (C4 (Web Text))

Max Activating Token Index: 337