Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1604 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1563581 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1398599 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1572226 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4210. Min Act: -0.0000

Data Index: 339967 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1389129 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1460424 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1629365 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1445398 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1546954 (Python Code)

Max Activating Token Index: 309

Text #9

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1455583 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1628564 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3618. Min Act: -0.0000

Data Index: 6648 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3774. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1147481 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1472023 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3560. Min Act: -0.0000

Data Index: 625024 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3326. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1395219 (Python Code)

Max Activating Token Index: 576

Text #19

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1410173 (Python Code)

Max Activating Token Index: 597