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

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

Neuron 660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.6748. Min Act: -0.0000

Data Index: 155746 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.6645. Min Act: -0.0000

Data Index: 82272 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.4791. Min Act: -0.0000

Data Index: 278542 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.2478. Min Act: -0.0000

Data Index: 883197 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.2467. Min Act: -0.0000

Data Index: 1327107 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.3164. Min Act: -0.0000

Data Index: 1217507 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.3073. Min Act: -0.0000

Data Index: 371120 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.3188. Min Act: -0.0000

Data Index: 1209080 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.0399. Min Act: -0.0000

Data Index: 1176178 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.1799. Min Act: -0.0000

Data Index: 625152 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.2727. Min Act: -0.0000

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.1517. Min Act: -0.0000

Data Index: 715037 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.1369. Min Act: -0.0000

Data Index: 33653 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.1332. Min Act: -0.0000

Data Index: 1023787 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.2237. Min Act: -0.0000

Data Index: 785314 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 3.6748. Min Range: -3.6748

Max Act: 3.0025. Min Act: -0.0000

Data Index: 1465107 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 3.6748. Min Range: -3.6748

Max Act: 2.8634. Min Act: -0.0000

Data Index: 541415 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.6748. Min Range: -3.6748

Max Act: 2.9662. Min Act: -0.0000

Data Index: 1103429 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 3.6748. Min Range: -3.6748

Max Act: 2.9610. Min Act: -0.0000

Data Index: 1183285 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.6748. Min Range: -3.6748

Max Act: 2.9555. Min Act: -0.0000

Data Index: 1217630 (C4 (Web Text))

Max Activating Token Index: 974