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

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

Neuron 151 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: 0.9094. Min Range: -0.9094

Max Act: 0.8920. Min Act: -0.0001

Data Index: 1133995 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8633. Min Act: -0.0001

Data Index: 2691 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8176. Min Act: -0.0001

Data Index: 49179 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8078. Min Act: -0.0001

Data Index: 1283847 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7936. Min Act: -0.0001

Data Index: 77608 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7297. Min Act: -0.0001

Data Index: 524006 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1224267 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7360. Min Act: -0.0001

Data Index: 263176 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7115. Min Act: -0.0001

Data Index: 635058 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7290. Min Act: -0.0001

Data Index: 867333 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.9094. Min Act: -0.0001

Data Index: 342419 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7533. Min Act: -0.0001

Data Index: 68508 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7480. Min Act: -0.0001

Data Index: 1259181 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6540. Min Act: -0.0001

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6495. Min Act: -0.0001

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6913. Min Act: -0.0001

Data Index: 1157892 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1287615 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1110826 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6418. Min Act: -0.0001

Data Index: 755485 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6582. Min Act: -0.0001

Data Index: 1328956 (C4 (Web Text))

Max Activating Token Index: 335