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

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

Neuron 4200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0249. Min Act: -0.0001

Data Index: 456205 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8524. Min Act: -0.0001

Data Index: 805417 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7591. Min Act: -0.0001

Data Index: 845297 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1121054 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7466. Min Act: -0.0001

Data Index: 580298 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7363. Min Act: -0.0001

Data Index: 4340 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7298. Min Act: -0.0001

Data Index: 229283 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1340615 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1133943 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7196. Min Act: -0.0001

Data Index: 821249 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7373. Min Act: -0.0001

Data Index: 1195943 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1236689 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6350. Min Act: -0.0001

Data Index: 528302 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6516. Min Act: -0.0001

Data Index: 419635 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7319. Min Act: -0.0001

Data Index: 814929 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7122. Min Act: -0.0001

Data Index: 177947 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6566. Min Act: -0.0001

Data Index: 380064 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.6554. Min Act: -0.0001

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7181. Min Act: -0.0001

Data Index: 507250 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7002. Min Act: -0.0001

Data Index: 596412 (C4 (Web Text))

Max Activating Token Index: 291