Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5421 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.4232. Min Act: -0.0002

Data Index: 156235 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.4263. Min Act: -0.0002

Data Index: 149158 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.4114. Min Act: -0.0002

Data Index: 446444 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.4080. Min Act: -0.0002

Data Index: 151773 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.3681. Min Act: -0.0002

Data Index: 601984 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2920. Min Act: -0.0002

Data Index: 127735 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.3119. Min Act: -0.0002

Data Index: 956747 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.3251. Min Act: -0.0002

Data Index: 808025 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2890. Min Act: -0.0002

Data Index: 1209578 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2954. Min Act: -0.0002

Data Index: 562272 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2978. Min Act: -0.0002

Data Index: 1359244 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2897. Min Act: -0.0002

Data Index: 462327 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.3040. Min Act: -0.0002

Data Index: 437754 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2637. Min Act: -0.0002

Data Index: 1009848 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2824. Min Act: -0.0002

Data Index: 469309 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2863. Min Act: -0.0002

Data Index: 231607 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2321. Min Act: -0.0002

Data Index: 532533 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2418. Min Act: -0.0002

Data Index: 1018150 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2209. Min Act: -0.0002

Data Index: 644681 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.4263. Min Range: -1.4263

Max Act: 1.2277. Min Act: -0.0002

Data Index: 8039 (C4 (Web Text))

Max Activating Token Index: 266