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

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

Neuron 2243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.6933. Min Act: -0.0000

Data Index: 1108834 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.5084. Min Act: -0.0000

Data Index: 841492 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2116. Min Act: -0.0000

Data Index: 530161 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.5314. Min Act: -0.0000

Data Index: 770692 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2273. Min Act: -0.0000

Data Index: 143452 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.6399. Min Act: -0.0000

Data Index: 28804 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3274. Min Act: -0.0000

Data Index: 951375 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4612. Min Act: -0.0000

Data Index: 199567 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4580. Min Act: -0.0000

Data Index: 726736 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3129. Min Act: -0.0000

Data Index: 947489 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.4390. Min Act: -0.0000

Data Index: 323133 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3001. Min Act: -0.0000

Data Index: 212959 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1722. Min Act: -0.0000

Data Index: 299359 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2870. Min Act: -0.0000

Data Index: 432662 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.2484. Min Act: -0.0000

Data Index: 1156407 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1510. Min Act: -0.0000

Data Index: 666487 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.1053. Min Act: -0.0000

Data Index: 1008434 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3513. Min Act: -0.0000

Data Index: 4500 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 2.6933. Min Range: -2.6933

Max Act: 2.3232. Min Act: -0.0000

Data Index: 1270986 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 2.6933. Min Range: -2.6933

Max Act: 1.9014. Min Act: -0.0000

Data Index: 88417 (C4 (Web Text))

Max Activating Token Index: 915