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

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

Neuron 5464 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: 3.5184. Min Range: -3.5184

Max Act: 3.5104. Min Act: -0.0001

Data Index: 1004365 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.2719. Min Act: -0.0001

Data Index: 897399 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.5184. Min Act: -0.0001

Data Index: 1112385 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.3615. Min Act: -0.0001

Data Index: 748215 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.1958. Min Act: -0.0001

Data Index: 21979 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 3.5184. Min Range: -3.5184

Max Act: 3.3449. Min Act: -0.0000

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.8154. Min Act: -0.0001

Data Index: 1284588 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.9070. Min Act: -0.0001

Data Index: 6448 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1151903 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.7602. Min Act: -0.0001

Data Index: 292358 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.5145. Min Act: -0.0001

Data Index: 409650 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.6057. Min Act: -0.0000

Data Index: 823244 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.8269. Min Act: -0.0001

Data Index: 760307 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.5442. Min Act: -0.0000

Data Index: 202472 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.5077. Min Act: -0.0001

Data Index: 89193 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.5564. Min Act: -0.0000

Data Index: 497628 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.4523. Min Act: -0.0000

Data Index: 737366 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.6762. Min Act: -0.0001

Data Index: 148627 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.6702. Min Act: -0.0001

Data Index: 1236358 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 3.5184. Min Range: -3.5184

Max Act: 2.1879. Min Act: -0.0000

Data Index: 927790 (C4 (Web Text))

Max Activating Token Index: 761