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

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

Neuron 4850 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: 0.8350. Min Range: -0.8350

Max Act: 0.8350. Min Act: -0.0000

Data Index: 741224 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.8302. Min Act: -0.0000

Data Index: 138189 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.7978. Min Act: -0.0000

Data Index: 666790 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1326295 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.7265. Min Act: 0.0000

Data Index: 205547 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6929. Min Act: -0.0000

Data Index: 577122 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.7312. Min Act: -0.0000

Data Index: 331627 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1235153 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6559. Min Act: 0.0000

Data Index: 601068 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1092167 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6175. Min Act: -0.0000

Data Index: 965265 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6309. Min Act: -0.0000

Data Index: 710592 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6033. Min Act: 0.0000

Data Index: 34927 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6440. Min Act: -0.0000

Data Index: 307902 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6178. Min Act: -0.0000

Data Index: 63449 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6169. Min Act: -0.0000

Data Index: 371788 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6095. Min Act: -0.0000

Data Index: 81970 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.5915. Min Act: -0.0000

Data Index: 267342 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6251. Min Act: -0.0000

Data Index: 829991 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.8350. Min Range: -0.8350

Max Act: 0.6036. Min Act: -0.0000

Data Index: 714574 (C4 (Web Text))

Max Activating Token Index: 7