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

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

Neuron 1650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.6501. Min Act: -0.0000

Data Index: 1270041 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.4863. Min Act: -0.0000

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.1977. Min Act: -0.0000

Data Index: 500215 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.1802. Min Act: -0.0000

Data Index: 318591 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.4320. Min Act: -0.0000

Data Index: 547948 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.0053. Min Act: -0.0000

Data Index: 355110 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.0944. Min Act: -0.0000

Data Index: 480098 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 2.6501. Min Range: -2.6501

Max Act: 2.0150. Min Act: -0.0000

Data Index: 132278 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.8417. Min Act: -0.0000

Data Index: 431783 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.6434. Min Act: -0.0000

Data Index: 448021 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.6685. Min Act: -0.0000

Data Index: 39625 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.6515. Min Act: -0.0000

Data Index: 249134 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5022. Min Act: -0.0000

Data Index: 924402 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1201373 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5881. Min Act: -0.0000

Data Index: 617857 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5164. Min Act: -0.0000

Data Index: 278147 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5427. Min Act: -0.0000

Data Index: 245968 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5012. Min Act: -0.0000

Data Index: 722477 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.4693. Min Act: -0.0000

Data Index: 1116794 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 2.6501. Min Range: -2.6501

Max Act: 1.5093. Min Act: -0.0000

Data Index: 169694 (C4 (Web Text))

Max Activating Token Index: 1009