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

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

Neuron 3217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2294. Min Act: -0.0001

Data Index: 503207 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2861. Min Act: -0.0001

Data Index: 1065928 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1041150 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1936. Min Act: -0.0001

Data Index: 252044 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1421. Min Act: -0.0001

Data Index: 770016 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0923. Min Act: -0.0001

Data Index: 1296719 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9958. Min Act: -0.0001

Data Index: 854301 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0616. Min Act: -0.0001

Data Index: 369773 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9879. Min Act: -0.0001

Data Index: 275458 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9751. Min Act: -0.0001

Data Index: 320947 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0327. Min Act: -0.0001

Data Index: 460139 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9974. Min Act: -0.0001

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9624. Min Act: -0.0001

Data Index: 1141275 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9166. Min Act: -0.0001

Data Index: 962680 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9253. Min Act: -0.0001

Data Index: 42165 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9726. Min Act: -0.0001

Data Index: 1113433 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9473. Min Act: -0.0001

Data Index: 999726 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0541. Min Act: -0.0001

Data Index: 395376 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9705. Min Act: -0.0001

Data Index: 200920 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1123514 (C4 (Web Text))

Max Activating Token Index: 718