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

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

Neuron 4450 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: 5.6284. Min Range: -5.6284

Max Act: 5.4624. Min Act: -0.0001

Data Index: 648741 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.6284. Min Act: -0.0001

Data Index: 339988 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.4345. Min Act: -0.0001

Data Index: 651257 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.3916. Min Act: -0.0001

Data Index: 1305707 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.2909. Min Act: -0.0001

Data Index: 920504 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.0946. Min Act: -0.0001

Data Index: 234052 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 5.6284. Min Range: -5.6284

Max Act: 5.0640. Min Act: -0.0001

Data Index: 492188 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.9568. Min Act: -0.0001

Data Index: 287135 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.8944. Min Act: -0.0001

Data Index: 744077 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.6656. Min Act: -0.0001

Data Index: 1179409 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.8312. Min Act: -0.0001

Data Index: 630400 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.6331. Min Act: -0.0001

Data Index: 1218945 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.6207. Min Act: -0.0001

Data Index: 648318 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.9472. Min Act: -0.0001

Data Index: 282230 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.9305. Min Act: -0.0001

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.5905. Min Act: -0.0001

Data Index: 233407 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.3999. Min Act: -0.0001

Data Index: 1218944 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.7357. Min Act: -0.0001

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.5821. Min Act: -0.0001

Data Index: 531236 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 5.6284. Min Range: -5.6284

Max Act: 4.9158. Min Act: -0.0001

Data Index: 1062326 (C4 (Web Text))

Max Activating Token Index: 139