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

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

Neuron 2063 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0003

Data Index: 902908 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0404. Min Act: -0.0003

Data Index: 14052 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1140028 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1292207 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0370. Min Act: -0.0003

Data Index: 290174 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1349151 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0329. Min Act: -0.0003

Data Index: 344586 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1058196 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1300006 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0320. Min Act: -0.0003

Data Index: 490823 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0316. Min Act: -0.0003

Data Index: 79160 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0300. Min Act: -0.0003

Data Index: 205497 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1061452 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1231584 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1232778 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0301. Min Act: -0.0003

Data Index: 885509 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0294. Min Act: -0.0003

Data Index: 905623 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1130085 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0322. Min Act: -0.0003

Data Index: 588078 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1010448 (C4 (Web Text))

Max Activating Token Index: 362