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

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

Neuron 2538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1189050 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3867. Min Act: -0.0000

Data Index: 292395 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4024. Min Act: -0.0000

Data Index: 722498 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3634. Min Act: -0.0000

Data Index: 505371 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3673. Min Act: -0.0000

Data Index: 61632 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1101552 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3480. Min Act: -0.0000

Data Index: 449546 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3255. Min Act: -0.0000

Data Index: 807588 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1290736 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3201. Min Act: -0.0000

Data Index: 260749 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3406. Min Act: -0.0000

Data Index: 416175 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3435. Min Act: -0.0000

Data Index: 39270 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3027. Min Act: -0.0000

Data Index: 576217 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3069. Min Act: -0.0000

Data Index: 658430 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3141. Min Act: -0.0000

Data Index: 492753 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2945. Min Act: -0.0000

Data Index: 429150 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2949. Min Act: -0.0000

Data Index: 837649 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1030902 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2785. Min Act: -0.0000

Data Index: 498424 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2546. Min Act: -0.0000

Data Index: 415218 (C4 (Web Text))

Max Activating Token Index: 996