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

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

Neuron 2920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1250091 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.3461. Min Act: -0.0000

Data Index: 540110 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2896. Min Act: -0.0000

Data Index: 395088 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1070955 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2509. Min Act: -0.0000

Data Index: 437520 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2015. Min Act: -0.0000

Data Index: 775192 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1030658 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1882. Min Act: -0.0000

Data Index: 213463 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1365782 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1144299 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1101696 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1500. Min Act: -0.0000

Data Index: 754510 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0558. Min Act: -0.0000

Data Index: 14365 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1001. Min Act: -0.0000

Data Index: 57201 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0576. Min Act: -0.0000

Data Index: 609332 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1307205 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0405. Min Act: -0.0000

Data Index: 330507 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.1341. Min Act: -0.0000

Data Index: 255954 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1024524 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.0714. Min Act: -0.0000

Data Index: 656062 (C4 (Web Text))

Max Activating Token Index: 587