Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1130 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3690. Min Act: -0.0001

Data Index: 549677 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3177. Min Act: -0.0001

Data Index: 570852 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1130705 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2824. Min Act: -0.0001

Data Index: 248868 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1000792 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2864. Min Act: -0.0001

Data Index: 245432 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3085. Min Act: -0.0001

Data Index: 1049098 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3204. Min Act: -0.0001

Data Index: 643331 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2972. Min Act: -0.0001

Data Index: 312427 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2951. Min Act: -0.0001

Data Index: 557757 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1203207 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2822. Min Act: -0.0001

Data Index: 580839 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1210633 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2618. Min Act: -0.0001

Data Index: 8188 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3070. Min Act: -0.0001

Data Index: 100306 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2769. Min Act: -0.0001

Data Index: 1284647 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2483. Min Act: -0.0001

Data Index: 44077 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1189643 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2849. Min Act: -0.0001

Data Index: 110402 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2635. Min Act: -0.0001

Data Index: 44453 (C4 (Web Text))

Max Activating Token Index: 188