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

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

Neuron 3431 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1259. Min Range: -2.1259

Max Act: 2.1259. Min Act: -0.0000

Data Index: 983949 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 2.1259. Min Range: -2.1259

Max Act: 1.3347. Min Act: -0.0000

Data Index: 859332 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 2.1259. Min Range: -2.1259

Max Act: 1.0143. Min Act: -0.0000

Data Index: 964801 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9928. Min Act: -0.0000

Data Index: 665025 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9823. Min Act: -0.0000

Data Index: 189526 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9598. Min Act: -0.0000

Data Index: 444524 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9523. Min Act: -0.0000

Data Index: 12657 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9562. Min Act: -0.0000

Data Index: 286132 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9015. Min Act: -0.0000

Data Index: 745296 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 2.1259. Min Range: -2.1259

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1628145 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1309115 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8933. Min Act: -0.0000

Data Index: 26447 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8366. Min Act: -0.0000

Data Index: 546128 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8808. Min Act: -0.0000

Data Index: 594287 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1489166 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1346978 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.9228. Min Act: -0.0000

Data Index: 692508 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1072585 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1145097 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.1259. Min Range: -2.1259

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1226996 (C4 (Web Text))

Max Activating Token Index: 716