Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1125219 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2901. Min Act: -0.0001

Data Index: 15681 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2777. Min Act: -0.0001

Data Index: 896281 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2673. Min Act: -0.0001

Data Index: 626830 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2644. Min Act: -0.0001

Data Index: 370592 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2418. Min Act: -0.0000

Data Index: 903001 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2782. Min Act: -0.0000

Data Index: 368322 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1357968 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1107439 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2832. Min Act: -0.0000

Data Index: 663253 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2791. Min Act: -0.0000

Data Index: 527618 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2468. Min Act: -0.0001

Data Index: 321695 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2562. Min Act: -0.0000

Data Index: 615250 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1011314 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2632. Min Act: -0.0000

Data Index: 312045 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2632. Min Act: -0.0000

Data Index: 135592 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2503. Min Act: -0.0001

Data Index: 253002 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1284520 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2482. Min Act: -0.0000

Data Index: 137304 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2522. Min Act: -0.0000

Data Index: 583117 (C4 (Web Text))

Max Activating Token Index: 327