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

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

Neuron 2141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.5260. Min Act: -0.0000

Data Index: 1532459 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.2904. Min Act: -0.0000

Data Index: 1645338 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1397797 (Python Code)

Max Activating Token Index: 336

Text #3

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.2754. Min Act: -0.0000

Data Index: 614352 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.3324. Min Act: -0.0000

Data Index: 1479081 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.2630. Min Act: -0.0000

Data Index: 775107 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.1255. Min Act: -0.0000

Data Index: 1497842 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.2241. Min Act: -0.0000

Data Index: 833650 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.2033. Min Act: -0.0000

Data Index: 939041 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.1235. Min Act: -0.0000

Data Index: 1585886 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.0829. Min Act: -0.0000

Data Index: 1277825 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.1593. Min Act: -0.0000

Data Index: 877191 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.1216. Min Act: -0.0000

Data Index: 1516835 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.1922. Min Act: -0.0000

Data Index: 1297778 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 2.5260. Min Range: -2.5260

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1357203 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.0505. Min Act: -0.0000

Data Index: 310304 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1168034 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 2.5260. Min Range: -2.5260

Max Act: 1.9263. Min Act: -0.0000

Data Index: 567394 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.0405. Min Act: -0.0000

Data Index: 973462 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.5260. Min Range: -2.5260

Max Act: 2.0010. Min Act: -0.0000

Data Index: 1185514 (C4 (Web Text))

Max Activating Token Index: 212