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

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

Neuron 2411 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: 2.5798. Min Range: -2.5798

Max Act: 2.5798. Min Act: -0.0002

Data Index: 656598 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2983. Min Act: -0.0002

Data Index: 61591 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.3667. Min Act: -0.0002

Data Index: 712982 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.3249. Min Act: -0.0002

Data Index: 980958 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2696. Min Act: -0.0002

Data Index: 958573 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2810. Min Act: -0.0002

Data Index: 48127 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.3065. Min Act: -0.0002

Data Index: 458734 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2117. Min Act: -0.0002

Data Index: 104207 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2252. Min Act: -0.0002

Data Index: 743262 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2379. Min Act: -0.0002

Data Index: 467716 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2138. Min Act: -0.0002

Data Index: 1280540 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2724. Min Act: -0.0002

Data Index: 1334237 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2337. Min Act: -0.0002

Data Index: 361461 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2216. Min Act: -0.0002

Data Index: 697680 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1916. Min Act: -0.0002

Data Index: 18757 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1875. Min Act: -0.0002

Data Index: 195404 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1278. Min Act: -0.0002

Data Index: 395973 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1869. Min Act: -0.0002

Data Index: 480909 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1197. Min Act: -0.0002

Data Index: 839524 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1127. Min Act: -0.0002

Data Index: 890203 (C4 (Web Text))

Max Activating Token Index: 704