Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4953. Min Act: -0.0001

Data Index: 900781 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3401. Min Act: -0.0001

Data Index: 540097 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3742. Min Act: -0.0001

Data Index: 124052 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3651. Min Act: -0.0001

Data Index: 1301877 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1125196 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1287897 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3375. Min Act: -0.0001

Data Index: 480078 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3297. Min Act: -0.0000

Data Index: 682933 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3495. Min Act: -0.0001

Data Index: 560117 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1080971 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3245. Min Act: -0.0001

Data Index: 571400 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3252. Min Act: -0.0001

Data Index: 175453 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1156884 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1133462 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3131. Min Act: -0.0001

Data Index: 328194 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3420. Min Act: -0.0001

Data Index: 1563334 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3229. Min Act: -0.0001

Data Index: 974343 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.2973. Min Act: -0.0001

Data Index: 853330 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1041229 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3221. Min Act: -0.0001

Data Index: 343895 (C4 (Web Text))

Max Activating Token Index: 156