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

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

Neuron 4320 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: 0.0448. Min Range: -0.0448

Max Act: 0.0432. Min Act: -0.0000

Data Index: 877447 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0000

Data Index: 226541 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0413. Min Act: -0.0000

Data Index: 485828 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0421. Min Act: -0.0000

Data Index: 105395 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0375. Min Act: -0.0000

Data Index: 73554 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0377. Min Act: -0.0000

Data Index: 975016 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1171824 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1444052 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1174025 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0368. Min Act: -0.0000

Data Index: 388034 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0351. Min Act: -0.0000

Data Index: 593379 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0349. Min Act: -0.0000

Data Index: 627054 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1090130 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0327. Min Act: -0.0000

Data Index: 207509 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0335. Min Act: -0.0000

Data Index: 942232 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1290934 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1212971 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0320. Min Act: -0.0000

Data Index: 548161 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0344. Min Act: -0.0000

Data Index: 583019 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1474777 (Python Code)

Max Activating Token Index: 22