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

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

Neuron 4063 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: 0.5338. Min Range: -0.5338

Max Act: 0.5338. Min Act: -0.0000

Data Index: 296553 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3972. Min Act: -0.0000

Data Index: 628612 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1269561 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1479507 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3792. Min Act: -0.0000

Data Index: 243022 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3461. Min Act: -0.0000

Data Index: 694151 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3539. Min Act: -0.0000

Data Index: 813767 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1099809 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2774. Min Act: -0.0000

Data Index: 871326 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1228644 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3030. Min Act: -0.0000

Data Index: 281523 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1617419 (Python Code)

Max Activating Token Index: 926

Text #12

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3107. Min Act: -0.0000

Data Index: 856797 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1121667 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2937. Min Act: -0.0000

Data Index: 952624 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2726. Min Act: -0.0000

Data Index: 988807 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1294210 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2934. Min Act: -0.0000

Data Index: 640809 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1225409 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.2589. Min Act: -0.0000

Data Index: 684408 (C4 (Web Text))

Max Activating Token Index: 689