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

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

Neuron 4175 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6345. Min Act: -0.0000

Data Index: 960899 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 68184 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6178. Min Act: -0.0000

Data Index: 958895 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1152507 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1236946 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5743. Min Act: -0.0000

Data Index: 181196 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5531. Min Act: -0.0000

Data Index: 648128 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1163830 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1312900 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4890. Min Act: -0.0000

Data Index: 273080 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4826. Min Act: -0.0001

Data Index: 49961 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1174872 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4966. Min Act: -0.0000

Data Index: 105560 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1283890 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4918. Min Act: -0.0000

Data Index: 282341 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4922. Min Act: -0.0000

Data Index: 398129 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4787. Min Act: -0.0001

Data Index: 873057 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4094. Min Act: -0.0000

Data Index: 616079 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1091035 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4255. Min Act: -0.0000

Data Index: 905991 (C4 (Web Text))

Max Activating Token Index: 712