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

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

Neuron 1494 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7794. Min Act: -0.0000

Data Index: 1606500 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1378007 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7316. Min Act: -0.0000

Data Index: 906803 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5957. Min Act: -0.0000

Data Index: 759532 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1203920 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1648206 (Python Code)

Max Activating Token Index: 320

Text #6

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.6355. Min Act: -0.0000

Data Index: 65040 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.4670. Min Act: -0.0000

Data Index: 903294 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1255389 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.6171. Min Act: -0.0000

Data Index: 339884 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7042. Min Act: -0.0001

Data Index: 1212883 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1624193 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7692. Min Act: -0.0000

Data Index: 1607963 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7665. Min Act: -0.0000

Data Index: 1647129 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7531. Min Act: -0.0000

Data Index: 1639728 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5704. Min Act: -0.0000

Data Index: 428819 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1542346 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5640. Min Act: -0.0000

Data Index: 576968 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5537. Min Act: -0.0000

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 301