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

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

Neuron 1323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2389. Min Range: -5.2389

Max Act: 4.7161. Min Act: -0.0000

Data Index: 821554 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 5.2389. Min Range: -5.2389

Max Act: 5.2389. Min Act: -0.0000

Data Index: 192705 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 5.2389. Min Range: -5.2389

Max Act: 4.4290. Min Act: -0.0000

Data Index: 311639 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 5.2389. Min Range: -5.2389

Max Act: 4.3036. Min Act: -0.0000

Data Index: 507749 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 5.2389. Min Range: -5.2389

Max Act: 4.0612. Min Act: -0.0000

Data Index: 1283831 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.8879. Min Act: -0.0000

Data Index: 498352 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 5.2389. Min Range: -5.2389

Max Act: 4.0616. Min Act: -0.0000

Data Index: 831949 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.9982. Min Act: -0.0000

Data Index: 115927 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.7829. Min Act: -0.0000

Data Index: 590406 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.9206. Min Act: -0.0000

Data Index: 1176268 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.8827. Min Act: -0.0000

Data Index: 1273378 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.4077. Min Act: -0.0000

Data Index: 845008 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.8844. Min Act: -0.0000

Data Index: 1081920 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.1562. Min Act: -0.0000

Data Index: 1030077 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.6025. Min Act: -0.0000

Data Index: 18530 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.5164. Min Act: -0.0000

Data Index: 356922 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.4411. Min Act: -0.0000

Data Index: 175578 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.4218. Min Act: -0.0000

Data Index: 973585 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.4414. Min Act: -0.0000

Data Index: 891320 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 5.2389. Min Range: -5.2389

Max Act: 3.5637. Min Act: -0.0000

Data Index: 281281 (C4 (Web Text))

Max Activating Token Index: 480