Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1547 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3099. Min Act: -0.0001

Data Index: 647643 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0001

Data Index: 313597 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3221. Min Act: -0.0001

Data Index: 323468 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3063. Min Act: -0.0001

Data Index: 55303 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3148. Min Act: -0.0001

Data Index: 744485 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3019. Min Act: -0.0001

Data Index: 214335 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2999. Min Act: -0.0001

Data Index: 489690 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2992. Min Act: -0.0001

Data Index: 303534 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3254. Min Act: -0.0001

Data Index: 857021 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2734. Min Act: -0.0001

Data Index: 869345 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2951. Min Act: -0.0001

Data Index: 125047 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1349324 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2905. Min Act: -0.0001

Data Index: 645963 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2803. Min Act: -0.0001

Data Index: 466965 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1310300 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2932. Min Act: -0.0001

Data Index: 1316881 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2741. Min Act: -0.0001

Data Index: 152536 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1275412 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2710. Min Act: -0.0001

Data Index: 573853 (C4 (Web Text))

Max Activating Token Index: 381