Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1036007 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0425. Min Act: -0.0000

Data Index: 108779 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1253935 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1162300 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0190. Min Act: -0.0000

Data Index: 791723 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9635. Min Act: -0.0000

Data Index: 806638 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9602. Min Act: -0.0000

Data Index: 261304 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9428. Min Act: -0.0000

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9598. Min Act: -0.0000

Data Index: 925781 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1006938 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9366. Min Act: -0.0000

Data Index: 257495 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8936. Min Act: -0.0000

Data Index: 964761 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8530. Min Act: -0.0000

Data Index: 680383 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1224234 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8436. Min Act: -0.0000

Data Index: 776877 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7795. Min Act: -0.0000

Data Index: 738264 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7566. Min Act: -0.0001

Data Index: 778843 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7510. Min Act: -0.0000

Data Index: 558113 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7423. Min Act: -0.0000

Data Index: 521950 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7875. Min Act: -0.0001

Data Index: 569202 (C4 (Web Text))

Max Activating Token Index: 505