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

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

Neuron 4356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.4261. Min Act: -0.0000

Data Index: 649445 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3611. Min Act: -0.0000

Data Index: 68000 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3839. Min Act: -0.0000

Data Index: 81508 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3315. Min Act: -0.0000

Data Index: 78020 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3539. Min Act: -0.0000

Data Index: 879189 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1476226 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3106. Min Act: -0.0000

Data Index: 901705 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1421735 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1091132 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3160. Min Act: -0.0000

Data Index: 109611 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1496024 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3093. Min Act: -0.0000

Data Index: 141111 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3251. Min Act: -0.0000

Data Index: 615199 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1640475 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3315. Min Act: -0.0000

Data Index: 819182 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1582508 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2989. Min Act: -0.0000

Data Index: 43353 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1178547 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1589829 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2655. Min Act: -0.0000

Data Index: 224019 (C4 (Web Text))

Max Activating Token Index: 23