Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4308 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1315360 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.4154. Min Act: -0.0001

Data Index: 283519 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3584. Min Act: -0.0001

Data Index: 620129 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3865. Min Act: -0.0001

Data Index: 835574 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3083. Min Act: -0.0001

Data Index: 633954 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3521. Min Act: -0.0001

Data Index: 89369 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3710. Min Act: -0.0001

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3461. Min Act: -0.0001

Data Index: 1448 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3436. Min Act: -0.0001

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3462. Min Act: -0.0001

Data Index: 1203224 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3513. Min Act: -0.0001

Data Index: 511649 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3461. Min Act: -0.0001

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1298862 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3340. Min Act: -0.0001

Data Index: 898821 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3260. Min Act: -0.0001

Data Index: 681019 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3430. Min Act: -0.0001

Data Index: 467998 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1117260 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1534470 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3605. Min Act: -0.0001

Data Index: 935450 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.4261. Min Range: -0.4261

Max Act: 0.3438. Min Act: -0.0001

Data Index: 541139 (C4 (Web Text))

Max Activating Token Index: 192