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

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

Neuron 2706 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: 0.4299. Min Range: -0.4299

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1189571 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3984. Min Act: -0.0000

Data Index: 874398 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1108135 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3700. Min Act: -0.0000

Data Index: 277658 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3799. Min Act: -0.0000

Data Index: 32768 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3952. Min Act: -0.0000

Data Index: 548990 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3607. Min Act: -0.0000

Data Index: 184904 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3565. Min Act: -0.0000

Data Index: 556684 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3491. Min Act: -0.0000

Data Index: 368796 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1205722 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3215. Min Act: -0.0000

Data Index: 265502 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1356823 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3273. Min Act: -0.0000

Data Index: 661072 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3283. Min Act: -0.0000

Data Index: 7157 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3272. Min Act: -0.0000

Data Index: 71486 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3405. Min Act: -0.0000

Data Index: 361657 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1149546 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1052301 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3322. Min Act: -0.0000

Data Index: 430061 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.4299. Min Range: -0.4299

Max Act: 0.3256. Min Act: -0.0000

Data Index: 928194 (C4 (Web Text))

Max Activating Token Index: 109