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

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

Neuron 3584 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: 1.3749. Min Range: -1.3749

Max Act: 1.3749. Min Act: -0.0002

Data Index: 818216 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3367. Min Act: -0.0002

Data Index: 530406 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3352. Min Act: -0.0003

Data Index: 1343074 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3228. Min Act: -0.0002

Data Index: 174565 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2529. Min Act: -0.0003

Data Index: 973067 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2007. Min Act: -0.0002

Data Index: 1172515 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1980. Min Act: -0.0002

Data Index: 19961 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1573. Min Act: -0.0002

Data Index: 699655 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1538. Min Act: -0.0002

Data Index: 105383 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1490. Min Act: -0.0002

Data Index: 813171 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1358. Min Act: -0.0002

Data Index: 299525 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1271. Min Act: -0.0002

Data Index: 1100512 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1248. Min Act: -0.0002

Data Index: 554133 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1535. Min Act: -0.0002

Data Index: 1257649 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1324. Min Act: -0.0003

Data Index: 973895 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1167. Min Act: -0.0003

Data Index: 656481 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1290. Min Act: -0.0002

Data Index: 109216 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1031. Min Act: -0.0002

Data Index: 745107 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0929. Min Act: -0.0003

Data Index: 787298 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0975. Min Act: -0.0002

Data Index: 801078 (C4 (Web Text))

Max Activating Token Index: 244