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

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

Neuron 3082 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: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0001

Data Index: 581442 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0068. Min Act: -0.0001

Data Index: 1293600 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1185834 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8806. Min Act: -0.0001

Data Index: 422119 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8533. Min Act: -0.0001

Data Index: 1201181 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8372. Min Act: -0.0001

Data Index: 39826 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1157928 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7718. Min Act: -0.0001

Data Index: 302272 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8050. Min Act: -0.0001

Data Index: 403129 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7690. Min Act: -0.0001

Data Index: 318829 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7096. Min Act: -0.0001

Data Index: 607859 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7501. Min Act: -0.0001

Data Index: 325031 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7681. Min Act: -0.0001

Data Index: 1324625 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.6784. Min Act: -0.0001

Data Index: 180364 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1312774 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.6672. Min Act: -0.0001

Data Index: 1076116 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7051. Min Act: -0.0001

Data Index: 1223894 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.6559. Min Act: -0.0001

Data Index: 59112 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7335. Min Act: -0.0001

Data Index: 943536 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7337. Min Act: -0.0001

Data Index: 571788 (C4 (Web Text))

Max Activating Token Index: 121