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

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

Neuron 4896 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.7474. Min Act: -0.0000

Data Index: 339692 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.8768. Min Act: -0.0000

Data Index: 264087 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.8261. Min Act: -0.0000

Data Index: 414959 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.6858. Min Act: -0.0000

Data Index: 617999 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.8009. Min Act: -0.0000

Data Index: 67914 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.7655. Min Act: -0.0000

Data Index: 19403 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.7389. Min Act: -0.0000

Data Index: 114118 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.8702. Min Act: -0.0000

Data Index: 280474 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.6156. Min Act: -0.0000

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.7521. Min Act: -0.0000

Data Index: 177020 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.7325. Min Act: -0.0000

Data Index: 671952 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.4794. Min Act: -0.0000

Data Index: 998009 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.5930. Min Act: -0.0000

Data Index: 292099 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.5440. Min Act: -0.0000

Data Index: 944268 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.5030. Min Act: -0.0000

Data Index: 675190 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.4377. Min Act: -0.0000

Data Index: 1239086 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.2773. Min Act: -0.0000

Data Index: 436504 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.2673. Min Act: -0.0000

Data Index: 663004 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.1996. Min Act: -0.0000

Data Index: 801960 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.8768. Min Range: -2.8768

Max Act: 2.2974. Min Act: -0.0000

Data Index: 257327 (C4 (Web Text))

Max Activating Token Index: 519