Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3583. Min Range: -3.3583

Max Act: 3.3583. Min Act: -0.0000

Data Index: 1229567 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.7097. Min Act: -0.0000

Data Index: 1042480 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.7959. Min Act: -0.0000

Data Index: 191383 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.5270. Min Act: -0.0000

Data Index: 986487 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.6243. Min Act: -0.0000

Data Index: 989998 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.4577. Min Act: -0.0000

Data Index: 1355909 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.4521. Min Act: -0.0000

Data Index: 796965 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.3965. Min Act: -0.0000

Data Index: 335353 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.3772. Min Act: -0.0000

Data Index: 1175823 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.5071. Min Act: -0.0000

Data Index: 225186 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.5060. Min Act: -0.0000

Data Index: 1078093 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.4090. Min Act: -0.0000

Data Index: 71843 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.4247. Min Act: -0.0000

Data Index: 1020616 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2850. Min Act: -0.0000

Data Index: 652190 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2685. Min Act: -0.0000

Data Index: 189047 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2273. Min Act: -0.0000

Data Index: 1252477 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2055. Min Act: -0.0000

Data Index: 115099 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2026. Min Act: -0.0000

Data Index: 812211 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.2945. Min Act: -0.0000

Data Index: 532892 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.3583. Min Range: -3.3583

Max Act: 2.1952. Min Act: -0.0000

Data Index: 421189 (C4 (Web Text))

Max Activating Token Index: 281