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

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

Neuron 73 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2698. Min Range: -1.2698

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1460172 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 1.2698. Min Range: -1.2698

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1656387 (Python Code)

Max Activating Token Index: 515

Text #2

Max Range: 1.2698. Min Range: -1.2698

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1401624 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1435641 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 1.2698. Min Range: -1.2698

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1414864 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1637531 (Python Code)

Max Activating Token Index: 315

Text #6

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9110. Min Act: -0.0000

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1431977 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8059. Min Act: -0.0000

Data Index: 43508 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1551570 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1398905 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9380. Min Act: -0.0000

Data Index: 868141 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1463356 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8183. Min Act: -0.0000

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8934. Min Act: -0.0000

Data Index: 672224 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9207. Min Act: -0.0000

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1461819 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1070095 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.7706. Min Act: -0.0000

Data Index: 172667 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.2698. Min Range: -1.2698

Max Act: 0.7167. Min Act: -0.0000

Data Index: 427620 (C4 (Web Text))

Max Activating Token Index: 883