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

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

Neuron 1231 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: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1242876 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1283871 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4501. Min Act: -0.0001

Data Index: 980156 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4351. Min Act: -0.0001

Data Index: 831709 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4170. Min Act: -0.0001

Data Index: 518622 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1063083 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3947. Min Act: -0.0001

Data Index: 1337394 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4183. Min Act: -0.0001

Data Index: 259068 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3844. Min Act: -0.0001

Data Index: 852627 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3631. Min Act: -0.0001

Data Index: 230452 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3850. Min Act: -0.0001

Data Index: 31301 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3684. Min Act: -0.0001

Data Index: 1356555 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3833. Min Act: -0.0001

Data Index: 1251311 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3581. Min Act: -0.0001

Data Index: 1174647 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4084. Min Act: -0.0001

Data Index: 999268 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3883. Min Act: -0.0001

Data Index: 1238942 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3620. Min Act: -0.0001

Data Index: 889035 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1326856 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4029. Min Act: -0.0001

Data Index: 168970 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3544. Min Act: -0.0001

Data Index: 1204354 (C4 (Web Text))

Max Activating Token Index: 9