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

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

Neuron 4538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7332. Min Act: -0.0000

Data Index: 1157394 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7686. Min Act: -0.0000

Data Index: 316111 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7412. Min Act: -0.0000

Data Index: 94340 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7314. Min Act: -0.0000

Data Index: 1224859 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7871. Min Act: -0.0000

Data Index: 748999 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7292. Min Act: -0.0001

Data Index: 726243 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.5107. Min Act: -0.0001

Data Index: 1237979 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.5119. Min Act: -0.0000

Data Index: 740478 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.6679. Min Act: -0.0001

Data Index: 1030512 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.5125. Min Act: -0.0000

Data Index: 723901 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.7142. Min Act: -0.0000

Data Index: 325264 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.4989. Min Act: -0.0000

Data Index: 386271 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.5359. Min Act: -0.0001

Data Index: 441754 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.4131. Min Act: -0.0001

Data Index: 1173023 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1141250 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.4891. Min Act: -0.0001

Data Index: 150605 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.5401. Min Act: -0.0001

Data Index: 822001 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.4316. Min Act: -0.0001

Data Index: 645270 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1169375 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.7871. Min Range: -1.7871

Max Act: 1.3276. Min Act: -0.0001

Data Index: 237354 (C4 (Web Text))

Max Activating Token Index: 37