Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3186 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3664. Min Range: -4.3664

Max Act: 4.3664. Min Act: -0.0000

Data Index: 200237 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 4.3664. Min Range: -4.3664

Max Act: 4.0162. Min Act: -0.0000

Data Index: 954937 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 4.3664. Min Range: -4.3664

Max Act: 4.3208. Min Act: -0.0000

Data Index: 441190 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.7058. Min Act: -0.0000

Data Index: 293892 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.8480. Min Act: -0.0000

Data Index: 1320488 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.7620. Min Act: -0.0001

Data Index: 778644 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.9078. Min Act: -0.0001

Data Index: 153374 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.6555. Min Act: -0.0000

Data Index: 88393 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.8254. Min Act: -0.0000

Data Index: 761119 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.7830. Min Act: -0.0000

Data Index: 520147 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.4417. Min Act: -0.0000

Data Index: 921663 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.9555. Min Act: -0.0000

Data Index: 406630 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.6518. Min Act: -0.0000

Data Index: 317977 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.5499. Min Act: -0.0000

Data Index: 686523 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.5606. Min Act: -0.0000

Data Index: 60087 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.3843. Min Act: -0.0000

Data Index: 594864 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.6635. Min Act: -0.0000

Data Index: 556181 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.6369. Min Act: -0.0000

Data Index: 21920 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.3992. Min Act: -0.0000

Data Index: 810279 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 4.3664. Min Range: -4.3664

Max Act: 3.3846. Min Act: -0.0000

Data Index: 1017823 (C4 (Web Text))

Max Activating Token Index: 271