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

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

Neuron 3373 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.4448. Min Act: -0.0000

Data Index: 503447 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3992. Min Act: -0.0000

Data Index: 589934 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3987. Min Act: -0.0000

Data Index: 321912 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3861. Min Act: -0.0000

Data Index: 393349 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3738. Min Act: -0.0000

Data Index: 876075 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3615. Min Act: -0.0000

Data Index: 799762 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3483. Min Act: -0.0000

Data Index: 398779 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3457. Min Act: -0.0000

Data Index: 894682 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1161722 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3305. Min Act: -0.0000

Data Index: 692113 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3381. Min Act: -0.0000

Data Index: 189153 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1040040 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3458. Min Act: -0.0000

Data Index: 106475 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3051. Min Act: -0.0000

Data Index: 439433 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3202. Min Act: 0.0000

Data Index: 1249240 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3181. Min Act: -0.0000

Data Index: 402805 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3028. Min Act: -0.0000

Data Index: 654602 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3213. Min Act: -0.0000

Data Index: 351530 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1309935 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3032. Min Act: -0.0000

Data Index: 238506 (C4 (Web Text))

Max Activating Token Index: 432