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

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

Neuron 4276 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: 0.6512. Min Range: -0.6512

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1161604 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1195210 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5631. Min Act: -0.0000

Data Index: 112539 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5342. Min Act: -0.0000

Data Index: 546028 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5256. Min Act: -0.0000

Data Index: 650478 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4742. Min Act: -0.0000

Data Index: 830514 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.5024. Min Act: -0.0000

Data Index: 256987 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4567. Min Act: -0.0000

Data Index: 323382 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4908. Min Act: -0.0000

Data Index: 316332 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4498. Min Act: -0.0000

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4784. Min Act: -0.0000

Data Index: 918969 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1096427 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4195. Min Act: -0.0000

Data Index: 359577 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4194. Min Act: -0.0000

Data Index: 460577 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4008. Min Act: -0.0000

Data Index: 132139 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.3871. Min Act: -0.0000

Data Index: 204865 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1340116 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4303. Min Act: -0.0000

Data Index: 927887 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.6512. Min Range: -0.6512

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 691