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

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

Neuron 53 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9380. Min Act: -0.0000

Data Index: 7208 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8897. Min Act: -0.0000

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8786. Min Act: -0.0000

Data Index: 74055 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1510517 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9221. Min Act: -0.0000

Data Index: 780499 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1263940 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1395129 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1181265 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8514. Min Act: -0.0000

Data Index: 518300 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8221. Min Act: -0.0000

Data Index: 521357 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8705. Min Act: -0.0000

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1268137 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1150258 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8851. Min Act: -0.0000

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8685. Min Act: -0.0000

Data Index: 230191 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1325519 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.9003. Min Act: -0.0000

Data Index: 572145 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8149. Min Act: -0.0000

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.9580. Min Range: -0.9580

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1603160 (Python Code)

Max Activating Token Index: 374