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

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

Neuron 3404 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: 1.3520. Min Range: -1.3520

Max Act: 1.3520. Min Act: -0.0001

Data Index: 88429 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3174. Min Act: -0.0001

Data Index: 1344662 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2635. Min Act: -0.0001

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1490. Min Act: -0.0001

Data Index: 933054 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1235. Min Act: -0.0001

Data Index: 1109590 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2323. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1230871 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0664. Min Act: -0.0001

Data Index: 821498 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0321. Min Act: -0.0001

Data Index: 1132437 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0646. Min Act: -0.0001

Data Index: 591480 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1156290 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9629. Min Act: -0.0001

Data Index: 554111 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0549. Min Act: -0.0001

Data Index: 27094 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9609. Min Act: -0.0001

Data Index: 729551 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9742. Min Act: -0.0001

Data Index: 829869 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9704. Min Act: -0.0001

Data Index: 472332 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0457. Min Act: -0.0001

Data Index: 296824 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9394. Min Act: -0.0001

Data Index: 300241 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9654. Min Act: -0.0001

Data Index: 843374 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9257. Min Act: -0.0001

Data Index: 844720 (C4 (Web Text))

Max Activating Token Index: 492