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

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

Neuron 2056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1342410 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3389. Min Act: -0.0001

Data Index: 498104 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2804. Min Act: -0.0001

Data Index: 647423 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2931. Min Act: -0.0001

Data Index: 992627 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2807. Min Act: -0.0000

Data Index: 60329 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2876. Min Act: -0.0001

Data Index: 411784 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2738. Min Act: -0.0001

Data Index: 702748 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2478. Min Act: -0.0001

Data Index: 26996 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3241. Min Act: -0.0000

Data Index: 89961 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2727. Min Act: -0.0000

Data Index: 128617 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3091. Min Act: -0.0001

Data Index: 13692 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2573. Min Act: -0.0000

Data Index: 877568 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2474. Min Act: -0.0001

Data Index: 887579 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2433. Min Act: -0.0000

Data Index: 394435 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2573. Min Act: -0.0001

Data Index: 1129874 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2146. Min Act: -0.0001

Data Index: 987916 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2334. Min Act: -0.0001

Data Index: 453693 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2518. Min Act: -0.0001

Data Index: 184884 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1199288 (C4 (Web Text))

Max Activating Token Index: 431