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

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

Neuron 1997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3593. Min Act: -0.0001

Data Index: 484857 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3298. Min Act: -0.0000

Data Index: 881019 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3149. Min Act: -0.0001

Data Index: 63746 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3154. Min Act: -0.0001

Data Index: 780616 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3148. Min Act: -0.0000

Data Index: 212306 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3198. Min Act: -0.0001

Data Index: 719402 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3140. Min Act: -0.0001

Data Index: 973329 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2989. Min Act: -0.0000

Data Index: 498165 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2981. Min Act: -0.0000

Data Index: 713978 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2654. Min Act: -0.0001

Data Index: 497199 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1054146 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2946. Min Act: -0.0000

Data Index: 753899 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1166408 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2579. Min Act: -0.0001

Data Index: 172355 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1307570 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2744. Min Act: -0.0000

Data Index: 355031 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2657. Min Act: -0.0001

Data Index: 642213 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1105605 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2599. Min Act: -0.0000

Data Index: 909676 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2497. Min Act: -0.0000

Data Index: 690179 (C4 (Web Text))

Max Activating Token Index: 273