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

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

Neuron 3054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.8572. Min Act: -0.0001

Data Index: 1208912 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.8470. Min Act: -0.0001

Data Index: 1107658 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7498. Min Act: -0.0001

Data Index: 1337797 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7345. Min Act: -0.0001

Data Index: 1306254 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7684. Min Act: -0.0001

Data Index: 343481 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7549. Min Act: -0.0001

Data Index: 475625 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7585. Min Act: -0.0001

Data Index: 197723 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.5459. Min Act: -0.0001

Data Index: 196160 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7503. Min Act: -0.0001

Data Index: 686489 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.8380. Min Act: -0.0001

Data Index: 1317962 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7572. Min Act: -0.0001

Data Index: 948284 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7389. Min Act: -0.0001

Data Index: 1296439 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6064. Min Act: -0.0001

Data Index: 119944 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6358. Min Act: -0.0001

Data Index: 128705 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.5969. Min Act: -0.0001

Data Index: 627533 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.5451. Min Act: -0.0001

Data Index: 13857 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6181. Min Act: -0.0001

Data Index: 132276 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.8572. Min Range: -1.8572

Max Act: 0.9796. Min Act: -0.0001

Data Index: 579107 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 1.8572. Min Range: -1.8572

Max Act: 0.9050. Min Act: -0.0001

Data Index: 5791 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.8572. Min Range: -1.8572

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1112988 (C4 (Web Text))

Max Activating Token Index: 524