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

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

Neuron 3933 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2794. Min Act: -0.0000

Data Index: 123412 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2974. Min Act: -0.0000

Data Index: 52867 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2819. Min Act: 0.0000

Data Index: 115062 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2797. Min Act: 0.0000

Data Index: 1239267 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2775. Min Act: -0.0000

Data Index: 974103 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1179239 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2483. Min Act: -0.0000

Data Index: 825771 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2615. Min Act: -0.0000

Data Index: 372562 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1131028 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2304. Min Act: -0.0000

Data Index: 633603 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1078510 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2298. Min Act: -0.0000

Data Index: 148806 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1035713 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2264. Min Act: -0.0000

Data Index: 487692 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2080. Min Act: -0.0000

Data Index: 880876 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2202. Min Act: -0.0000

Data Index: 754802 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2056. Min Act: -0.0000

Data Index: 962498 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2092. Min Act: -0.0000

Data Index: 580842 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2119. Min Act: 0.0000

Data Index: 337074 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2045. Min Act: 0.0000

Data Index: 345721 (C4 (Web Text))

Max Activating Token Index: 324