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

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

Neuron 4035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1317649 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7967. Min Act: -0.0001

Data Index: 398660 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1347579 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7758. Min Act: -0.0001

Data Index: 1041555 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7522. Min Act: -0.0001

Data Index: 47348 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7912. Min Act: -0.0001

Data Index: 1102360 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6292. Min Act: -0.0001

Data Index: 147381 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1043433 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6928. Min Act: -0.0001

Data Index: 999995 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1047770 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6358. Min Act: -0.0001

Data Index: 223395 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6123. Min Act: -0.0001

Data Index: 492882 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6930. Min Act: -0.0001

Data Index: 1082375 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.5930. Min Act: -0.0001

Data Index: 50020 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7593. Min Act: -0.0001

Data Index: 649435 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6269. Min Act: -0.0001

Data Index: 786759 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6079. Min Act: -0.0001

Data Index: 1057356 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6362. Min Act: -0.0001

Data Index: 80994 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6964. Min Act: -0.0001

Data Index: 875676 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7672. Min Act: -0.0001

Data Index: 578704 (C4 (Web Text))

Max Activating Token Index: 162