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

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

Neuron 3860 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: 0.9955. Min Range: -0.9955

Max Act: 0.9955. Min Act: -0.0000

Data Index: 60254 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1256320 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6724. Min Act: -0.0000

Data Index: 858166 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6987. Min Act: -0.0000

Data Index: 443255 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6415. Min Act: -0.0000

Data Index: 102543 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6518. Min Act: -0.0000

Data Index: 422948 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6559. Min Act: -0.0000

Data Index: 3809 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.6268. Min Act: -0.0000

Data Index: 172135 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5903. Min Act: -0.0000

Data Index: 227110 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1002385 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5230. Min Act: -0.0000

Data Index: 285469 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5471. Min Act: -0.0000

Data Index: 906778 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1015368 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.4803. Min Act: -0.0000

Data Index: 947659 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5034. Min Act: -0.0000

Data Index: 355486 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5192. Min Act: -0.0000

Data Index: 720610 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.4946. Min Act: -0.0000

Data Index: 944290 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1153643 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.4899. Min Act: -0.0000

Data Index: 352117 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.9955. Min Range: -0.9955

Max Act: 0.4909. Min Act: -0.0000

Data Index: 242564 (C4 (Web Text))

Max Activating Token Index: 338