Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5909 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4070. Min Range: -4.4070

Max Act: 4.4070. Min Act: -0.0000

Data Index: 1215847 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 4.4070. Min Range: -4.4070

Max Act: 3.6912. Min Act: -0.0000

Data Index: 804187 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 4.4070. Min Range: -4.4070

Max Act: 3.7481. Min Act: -0.0000

Data Index: 35199 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.4070. Min Range: -4.4070

Max Act: 3.6686. Min Act: -0.0000

Data Index: 1050997 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.9801. Min Act: -0.0000

Data Index: 365186 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.9770. Min Act: -0.0000

Data Index: 572865 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 4.4070. Min Range: -4.4070

Max Act: 3.0776. Min Act: -0.0000

Data Index: 27261 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.8916. Min Act: -0.0000

Data Index: 512699 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.7435. Min Act: -0.0000

Data Index: 505302 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.7252. Min Act: -0.0000

Data Index: 57497 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.8236. Min Act: -0.0000

Data Index: 966426 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.8042. Min Act: -0.0000

Data Index: 552320 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1293147 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.5749. Min Act: -0.0000

Data Index: 615952 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.5105. Min Act: -0.0000

Data Index: 932972 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.1415. Min Act: -0.0000

Data Index: 73819 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.6304. Min Act: -0.0000

Data Index: 269090 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.4829. Min Act: -0.0000

Data Index: 267856 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.4798. Min Act: -0.0000

Data Index: 683927 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 4.4070. Min Range: -4.4070

Max Act: 2.4557. Min Act: -0.0000

Data Index: 103423 (C4 (Web Text))

Max Activating Token Index: 623