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

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

Neuron 6029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1553850 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1551142 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2612. Min Act: -0.0001

Data Index: 1622718 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1461072 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1369417 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1548446 (Python Code)

Max Activating Token Index: 544

Text #6

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1464836 (Python Code)

Max Activating Token Index: 521

Text #7

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1580626 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1584114 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1550606 (Python Code)

Max Activating Token Index: 512

Text #10

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1516888 (Python Code)

Max Activating Token Index: 865

Text #11

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2325. Min Act: -0.0001

Data Index: 1372109 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1371247 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1600549 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1653320 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1609591 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1456203 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1646138 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1456493 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1587552 (Python Code)

Max Activating Token Index: 485