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

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

Neuron 2991 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.4693. Min Act: -0.0001

Data Index: 863812 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.4291. Min Act: -0.0001

Data Index: 882562 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3885. Min Act: -0.0001

Data Index: 364234 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3991. Min Act: -0.0001

Data Index: 969199 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.4007. Min Act: -0.0001

Data Index: 309034 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3880. Min Act: -0.0001

Data Index: 149545 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3834. Min Act: -0.0001

Data Index: 15854 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3967. Min Act: -0.0001

Data Index: 1108313 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3671. Min Act: -0.0001

Data Index: 517600 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3507. Min Act: -0.0001

Data Index: 950770 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3390. Min Act: -0.0001

Data Index: 302599 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3491. Min Act: -0.0001

Data Index: 163774 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1099305 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3492. Min Act: -0.0001

Data Index: 70546 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3455. Min Act: -0.0001

Data Index: 480197 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3473. Min Act: -0.0001

Data Index: 422513 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1173219 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1047223 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3162. Min Act: -0.0001

Data Index: 579038 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.4693. Min Range: -0.4693

Max Act: 0.3117. Min Act: -0.0001

Data Index: 689116 (C4 (Web Text))

Max Activating Token Index: 701