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

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

Neuron 2637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5446. Min Range: -1.5446

Max Act: 1.5446. Min Act: -0.0000

Data Index: 118262 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 1.5446. Min Range: -1.5446

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1106520 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.5446. Min Range: -1.5446

Max Act: 1.0256. Min Act: -0.0000

Data Index: 280032 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.5446. Min Range: -1.5446

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1557180 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9930. Min Act: -0.0000

Data Index: 953201 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1489127 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1428334 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 1.5446. Min Range: -1.5446

Max Act: 1.0464. Min Act: -0.0000

Data Index: 623406 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9922. Min Act: -0.0000

Data Index: 497354 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1245132 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1206203 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9460. Min Act: -0.0000

Data Index: 542552 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1245343 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8883. Min Act: -0.0000

Data Index: 884261 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8885. Min Act: -0.0000

Data Index: 242637 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1327751 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1191866 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8599. Min Act: -0.0000

Data Index: 805396 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.5446. Min Range: -1.5446

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1511932 (Python Code)

Max Activating Token Index: 752