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

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

Neuron 263 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: 0.4881. Min Range: -0.4881

Max Act: 0.4881. Min Act: -0.0001

Data Index: 691648 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4439. Min Act: -0.0000

Data Index: 613366 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4389. Min Act: -0.0000

Data Index: 126415 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1328091 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4518. Min Act: -0.0001

Data Index: 859744 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4311. Min Act: -0.0000

Data Index: 415211 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4107. Min Act: -0.0000

Data Index: 322428 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4315. Min Act: -0.0001

Data Index: 566962 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1084574 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1293924 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1041651 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1020654 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4278. Min Act: -0.0000

Data Index: 496306 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3870. Min Act: -0.0000

Data Index: 355691 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1252728 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4041. Min Act: -0.0000

Data Index: 89567 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1179105 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3602. Min Act: -0.0001

Data Index: 420404 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3943. Min Act: -0.0001

Data Index: 178393 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1246331 (C4 (Web Text))

Max Activating Token Index: 864