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

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

Neuron 2307 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4981. Min Act: 0.0000

Data Index: 876204 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4285. Min Act: -0.0000

Data Index: 315535 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4281. Min Act: -0.0000

Data Index: 383487 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4233. Min Act: -0.0000

Data Index: 639001 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4035. Min Act: -0.0000

Data Index: 462363 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3975. Min Act: -0.0000

Data Index: 357711 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.4081. Min Act: -0.0000

Data Index: 728206 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3791. Min Act: -0.0000

Data Index: 932526 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3483. Min Act: 0.0002

Data Index: 679972 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3737. Min Act: -0.0000

Data Index: 103098 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3862. Min Act: 0.0001

Data Index: 53875 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3484. Min Act: -0.0000

Data Index: 805595 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3465. Min Act: -0.0000

Data Index: 891022 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3556. Min Act: 0.0003

Data Index: 887499 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3307. Min Act: -0.0000

Data Index: 468034 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3464. Min Act: -0.0000

Data Index: 9676 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1187052 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3295. Min Act: 0.0001

Data Index: 658014 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3416. Min Act: -0.0000

Data Index: 942108 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.4981. Min Range: -0.4981

Max Act: 0.3323. Min Act: 0.0000

Data Index: 48935 (C4 (Web Text))

Max Activating Token Index: 161