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

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

Neuron 1299 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1026460 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1037436 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0911. Min Act: -0.0002

Data Index: 249138 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0002

Data Index: 438587 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0952. Min Act: -0.0002

Data Index: 801147 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0002

Data Index: 47221 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1296945 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0915. Min Act: -0.0002

Data Index: 363119 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0845. Min Act: -0.0002

Data Index: 267414 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0846. Min Act: -0.0002

Data Index: 572958 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1288322 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0855. Min Act: -0.0002

Data Index: 452224 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1029964 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0728. Min Act: -0.0002

Data Index: 968119 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0800. Min Act: -0.0002

Data Index: 27901 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0793. Min Act: -0.0002

Data Index: 811501 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0797. Min Act: -0.0002

Data Index: 236982 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0776. Min Act: -0.0002

Data Index: 458089 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0808. Min Act: -0.0002

Data Index: 337714 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1183506 (C4 (Web Text))

Max Activating Token Index: 406