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

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

Neuron 515 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: 1.6497. Min Range: -1.6497

Max Act: 1.6497. Min Act: -0.0002

Data Index: 1084904 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.5756. Min Act: -0.0002

Data Index: 333563 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.4425. Min Act: -0.0002

Data Index: 753134 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3186. Min Act: -0.0002

Data Index: 602370 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.3303. Min Act: -0.0002

Data Index: 864701 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.2949. Min Act: -0.0003

Data Index: 1213002 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.2530. Min Act: -0.0002

Data Index: 660345 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.2463. Min Act: -0.0002

Data Index: 1194362 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.2183. Min Act: -0.0002

Data Index: 149205 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.2298. Min Act: -0.0002

Data Index: 999081 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0969. Min Act: -0.0002

Data Index: 521948 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0793. Min Act: -0.0002

Data Index: 511043 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0614. Min Act: -0.0002

Data Index: 608779 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0679. Min Act: -0.0002

Data Index: 660653 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0419. Min Act: -0.0002

Data Index: 270745 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0568. Min Act: -0.0002

Data Index: 379428 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0405. Min Act: -0.0002

Data Index: 550340 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.6497. Min Range: -1.6497

Max Act: 1.0123. Min Act: -0.0002

Data Index: 430732 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.6497. Min Range: -1.6497

Max Act: 0.9822. Min Act: -0.0003

Data Index: 1317474 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.6497. Min Range: -1.6497

Max Act: 0.9988. Min Act: -0.0002

Data Index: 793394 (C4 (Web Text))

Max Activating Token Index: 254