Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1252 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.4052. Min Act: -0.0001

Data Index: 509376 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3571. Min Act: -0.0001

Data Index: 929825 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3445. Min Act: -0.0001

Data Index: 75980 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1254168 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3292. Min Act: -0.0001

Data Index: 941527 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3140. Min Act: -0.0001

Data Index: 131531 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1344770 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3127. Min Act: -0.0001

Data Index: 1114901 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3028. Min Act: -0.0001

Data Index: 755739 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1154226 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2962. Min Act: -0.0001

Data Index: 682237 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.3227. Min Act: -0.0001

Data Index: 878798 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2725. Min Act: -0.0001

Data Index: 161136 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2795. Min Act: -0.0001

Data Index: 393560 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2676. Min Act: -0.0001

Data Index: 415444 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2463. Min Act: -0.0001

Data Index: 252429 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2746. Min Act: -0.0001

Data Index: 477948 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2504. Min Act: -0.0001

Data Index: 588020 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2613. Min Act: -0.0001

Data Index: 292096 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.4052. Min Range: -0.4052

Max Act: 0.2456. Min Act: -0.0001

Data Index: 833751 (C4 (Web Text))

Max Activating Token Index: 861