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

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

Neuron 1075 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: 1.3204. Min Range: -1.3204

Max Act: 1.3204. Min Act: -0.0001

Data Index: 630327 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.9821. Min Act: -0.0001

Data Index: 360910 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.3204. Min Range: -1.3204

Max Act: 1.0060. Min Act: -0.0001

Data Index: 133659 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.8014. Min Act: -0.0001

Data Index: 832235 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.8954. Min Act: -0.0001

Data Index: 739633 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.6822. Min Act: -0.0001

Data Index: 824055 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7760. Min Act: -0.0001

Data Index: 89827 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1134502 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7805. Min Act: -0.0001

Data Index: 136207 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1332849 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1064400 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7555. Min Act: -0.0001

Data Index: 86146 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7293. Min Act: -0.0001

Data Index: 402072 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.6788. Min Act: -0.0001

Data Index: 825607 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.6741. Min Act: -0.0001

Data Index: 544959 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.6924. Min Act: -0.0001

Data Index: 531207 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7118. Min Act: -0.0001

Data Index: 1058269 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7312. Min Act: -0.0001

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.6788. Min Act: -0.0001

Data Index: 51885 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.3204. Min Range: -1.3204

Max Act: 0.7392. Min Act: -0.0001

Data Index: 124179 (C4 (Web Text))

Max Activating Token Index: 178