Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3560 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.1988. Min Act: -0.0001

Data Index: 668790 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0217. Min Act: -0.0001

Data Index: 1165380 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.1218. Min Act: -0.0001

Data Index: 741259 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0011. Min Act: -0.0001

Data Index: 1221312 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9670. Min Act: -0.0001

Data Index: 824556 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1052596 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9629. Min Act: -0.0001

Data Index: 5925 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0339. Min Act: -0.0001

Data Index: 309554 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9247. Min Act: -0.0001

Data Index: 310996 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0368. Min Act: -0.0001

Data Index: 455280 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1178843 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8163. Min Act: -0.0001

Data Index: 1172140 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8612. Min Act: -0.0001

Data Index: 871465 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1155780 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8428. Min Act: -0.0001

Data Index: 416781 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8305. Min Act: -0.0001

Data Index: 316475 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1253267 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.7900. Min Act: -0.0001

Data Index: 423738 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.7469. Min Act: -0.0001

Data Index: 540790 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8062. Min Act: -0.0001

Data Index: 1301810 (C4 (Web Text))

Max Activating Token Index: 344