Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.6322. Min Act: -0.0001

Data Index: 351274 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1151800 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4684. Min Act: -0.0001

Data Index: 272273 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.5136. Min Act: -0.0001

Data Index: 225996 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4952. Min Act: -0.0001

Data Index: 878193 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4696. Min Act: -0.0001

Data Index: 731286 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4913. Min Act: -0.0001

Data Index: 974480 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4857. Min Act: -0.0001

Data Index: 521321 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4794. Min Act: -0.0001

Data Index: 224021 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4775. Min Act: -0.0001

Data Index: 142327 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4626. Min Act: -0.0001

Data Index: 805188 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4437. Min Act: -0.0001

Data Index: 939628 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4692. Min Act: -0.0001

Data Index: 46293 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4633. Min Act: -0.0001

Data Index: 1114161 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4623. Min Act: -0.0001

Data Index: 95885 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1076263 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4594. Min Act: -0.0001

Data Index: 1006678 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4597. Min Act: -0.0001

Data Index: 116267 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4352. Min Act: -0.0001

Data Index: 1085586 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.6322. Min Range: -0.6322

Max Act: 0.4517. Min Act: -0.0001

Data Index: 397993 (C4 (Web Text))

Max Activating Token Index: 208