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

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

Neuron 4034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1045969 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4584. Min Act: -0.0000

Data Index: 697115 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4543. Min Act: -0.0000

Data Index: 428633 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4334. Min Act: -0.0000

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4165. Min Act: -0.0000

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4405. Min Act: -0.0000

Data Index: 386553 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4006. Min Act: -0.0000

Data Index: 774712 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1271521 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3953. Min Act: -0.0000

Data Index: 453087 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1537064 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3438. Min Act: -0.0000

Data Index: 761856 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1350011 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1538143 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1543743 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1646624 (Python Code)

Max Activating Token Index: 275

Text #15

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1227896 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1332918 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1411532 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3070. Min Act: -0.0000

Data Index: 353391 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3173. Min Act: -0.0000

Data Index: 38925 (C4 (Web Text))

Max Activating Token Index: 775