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

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

Neuron 1297 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1118066 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3433. Min Act: -0.0000

Data Index: 365661 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3587. Min Act: -0.0001

Data Index: 1354085 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3382. Min Act: -0.0001

Data Index: 865473 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1193595 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3070. Min Act: -0.0000

Data Index: 970492 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1220385 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3016. Min Act: -0.0000

Data Index: 475034 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3088. Min Act: -0.0001

Data Index: 312095 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.3065. Min Act: -0.0001

Data Index: 406608 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2853. Min Act: -0.0001

Data Index: 471075 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2845. Min Act: -0.0000

Data Index: 571385 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2809. Min Act: -0.0001

Data Index: 638643 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2769. Min Act: -0.0000

Data Index: 403069 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2841. Min Act: -0.0001

Data Index: 264351 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1292424 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1107546 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2618. Min Act: -0.0000

Data Index: 503256 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2891. Min Act: -0.0000

Data Index: 116258 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.3639. Min Range: -0.3639

Max Act: 0.2592. Min Act: -0.0001

Data Index: 48217 (C4 (Web Text))

Max Activating Token Index: 836