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

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

Neuron 738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0591. Min Range: -1.0591

Max Act: 1.0591. Min Act: -0.0000

Data Index: 293757 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.0591. Min Range: -1.0591

Max Act: 1.0443. Min Act: -0.0000

Data Index: 218631 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.0591. Min Range: -1.0591

Max Act: 1.0480. Min Act: -0.0000

Data Index: 496472 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1357151 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8489. Min Act: -0.0000

Data Index: 858917 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8189. Min Act: -0.0000

Data Index: 84471 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7656. Min Act: -0.0000

Data Index: 170879 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8493. Min Act: -0.0000

Data Index: 325704 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8473. Min Act: -0.0000

Data Index: 805844 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8031. Min Act: -0.0000

Data Index: 914651 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8262. Min Act: -0.0000

Data Index: 289301 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1121001 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6666. Min Act: -0.0000

Data Index: 430734 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1318103 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7775. Min Act: -0.0000

Data Index: 890623 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6939. Min Act: -0.0000

Data Index: 339205 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7808. Min Act: -0.0000

Data Index: 611075 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7549. Min Act: -0.0000

Data Index: 245112 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.5898. Min Act: -0.0000

Data Index: 93831 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1033363 (C4 (Web Text))

Max Activating Token Index: 956