Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1898 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0005

Data Index: 703740 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4235. Min Act: -0.0005

Data Index: 255871 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4549. Min Act: -0.0005

Data Index: 721094 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4038. Min Act: -0.0005

Data Index: 235495 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4134. Min Act: -0.0005

Data Index: 8305 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3926. Min Act: -0.0005

Data Index: 69671 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3873. Min Act: -0.0005

Data Index: 138619 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3952. Min Act: -0.0005

Data Index: 1082580 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3660. Min Act: -0.0005

Data Index: 1023435 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3476. Min Act: -0.0005

Data Index: 312967 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3545. Min Act: -0.0005

Data Index: 878946 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3445. Min Act: -0.0005

Data Index: 216029 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3783. Min Act: -0.0005

Data Index: 803464 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3089. Min Act: -0.0004

Data Index: 20586 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3394. Min Act: -0.0005

Data Index: 1116423 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3536. Min Act: -0.0005

Data Index: 729910 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3401. Min Act: -0.0005

Data Index: 887030 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3498. Min Act: -0.0005

Data Index: 494702 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3473. Min Act: -0.0005

Data Index: 403178 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3448. Min Act: -0.0005

Data Index: 491305 (C4 (Web Text))

Max Activating Token Index: 225