Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5080. Min Act: -0.0001

Data Index: 944681 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5299. Min Act: -0.0001

Data Index: 461438 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4790. Min Act: -0.0001

Data Index: 1295805 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4533. Min Act: -0.0001

Data Index: 674983 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5197. Min Act: -0.0001

Data Index: 670390 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4930. Min Act: -0.0001

Data Index: 853342 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4938. Min Act: -0.0001

Data Index: 200262 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4916. Min Act: -0.0001

Data Index: 375346 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1112272 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5186. Min Act: -0.0001

Data Index: 271731 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4514. Min Act: -0.0001

Data Index: 1284653 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4648. Min Act: -0.0001

Data Index: 311920 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4596. Min Act: -0.0001

Data Index: 464123 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4877. Min Act: -0.0001

Data Index: 379141 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4710. Min Act: -0.0001

Data Index: 1328468 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4497. Min Act: -0.0001

Data Index: 669394 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1178854 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1349047 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1274523 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4492. Min Act: -0.0001

Data Index: 307888 (C4 (Web Text))

Max Activating Token Index: 253