Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 868 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4587. Min Act: -0.0000

Data Index: 99716 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1222849 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4195. Min Act: -0.0000

Data Index: 72759 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1196441 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4244. Min Act: -0.0000

Data Index: 512243 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4225. Min Act: -0.0000

Data Index: 437685 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4210. Min Act: -0.0000

Data Index: 197636 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1127987 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4066. Min Act: -0.0000

Data Index: 930546 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3945. Min Act: 0.0000

Data Index: 256859 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3753. Min Act: -0.0000

Data Index: 47391 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3660. Min Act: -0.0000

Data Index: 354458 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3765. Min Act: -0.0000

Data Index: 881183 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3855. Min Act: -0.0000

Data Index: 539179 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3900. Min Act: -0.0000

Data Index: 661132 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3514. Min Act: -0.0000

Data Index: 331192 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3605. Min Act: -0.0000

Data Index: 158438 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3624. Min Act: -0.0000

Data Index: 249058 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1168371 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3377. Min Act: -0.0000

Data Index: 356060 (C4 (Web Text))

Max Activating Token Index: 568