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

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

Neuron 5133 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: 1.7858. Min Range: -1.7858

Max Act: 1.7858. Min Act: -0.0000

Data Index: 47849 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7501. Min Act: -0.0000

Data Index: 56102 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.5972. Min Act: -0.0000

Data Index: 317518 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1602422 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4208. Min Act: -0.0000

Data Index: 218113 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4087. Min Act: -0.0000

Data Index: 318375 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1365673 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4104. Min Act: -0.0000

Data Index: 503669 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3509. Min Act: -0.0000

Data Index: 28560 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.4195. Min Act: -0.0000

Data Index: 690946 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1503735 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1455531 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3115. Min Act: -0.0000

Data Index: 629668 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3707. Min Act: -0.0000

Data Index: 544030 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3261. Min Act: -0.0000

Data Index: 49730 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.3003. Min Act: -0.0000

Data Index: 397663 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.2993. Min Act: -0.0000

Data Index: 694697 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1646536 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1619358 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1160948 (C4 (Web Text))

Max Activating Token Index: 772