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

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

Neuron 3246 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8389. Min Act: -0.0002

Data Index: 1023670 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8747. Min Act: -0.0002

Data Index: 515221 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.7802. Min Act: -0.0001

Data Index: 93976 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.9821. Min Act: -0.0001

Data Index: 835120 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8470. Min Act: -0.0001

Data Index: 305850 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.8167. Min Act: -0.0002

Data Index: 1305879 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.7066. Min Act: -0.0002

Data Index: 304208 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.7430. Min Act: -0.0002

Data Index: 535448 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6145. Min Act: -0.0002

Data Index: 605974 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6148. Min Act: -0.0001

Data Index: 1331399 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6072. Min Act: -0.0002

Data Index: 31779 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.3610. Min Act: -0.0001

Data Index: 533311 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6257. Min Act: -0.0001

Data Index: 841585 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6112. Min Act: -0.0002

Data Index: 769050 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5861. Min Act: -0.0001

Data Index: 527075 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.5168. Min Act: -0.0002

Data Index: 1309234 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4346. Min Act: -0.0002

Data Index: 206676 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.6142. Min Act: -0.0001

Data Index: 1138591 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4587. Min Act: -0.0001

Data Index: 631597 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.9821. Min Range: -1.9821

Max Act: 1.4802. Min Act: -0.0001

Data Index: 357325 (C4 (Web Text))

Max Activating Token Index: 65