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

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

Neuron 387 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: 0.5641. Min Range: -0.5641

Max Act: 0.5641. Min Act: -0.0001

Data Index: 47348 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5520. Min Act: -0.0001

Data Index: 425720 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1070940 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4811. Min Act: -0.0001

Data Index: 998216 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4800. Min Act: -0.0001

Data Index: 979095 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4490. Min Act: -0.0001

Data Index: 1245059 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4727. Min Act: -0.0001

Data Index: 778569 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4765. Min Act: -0.0001

Data Index: 1135881 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4244. Min Act: -0.0001

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4437. Min Act: -0.0001

Data Index: 1149487 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4596. Min Act: -0.0001

Data Index: 448449 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4534. Min Act: -0.0001

Data Index: 775547 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4585. Min Act: -0.0001

Data Index: 546827 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4227. Min Act: -0.0001

Data Index: 309272 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4381. Min Act: -0.0001

Data Index: 988333 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1282938 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4381. Min Act: -0.0001

Data Index: 872168 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4221. Min Act: -0.0001

Data Index: 191789 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1088966 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4168. Min Act: -0.0001

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 643