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

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

Neuron 2909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.4201. Min Act: -0.0001

Data Index: 552901 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1120804 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3828. Min Act: -0.0001

Data Index: 117468 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3554. Min Act: -0.0001

Data Index: 433031 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3611. Min Act: -0.0000

Data Index: 263181 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3416. Min Act: -0.0000

Data Index: 596575 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3265. Min Act: -0.0001

Data Index: 838599 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3446. Min Act: -0.0001

Data Index: 210687 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1299668 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2935. Min Act: -0.0001

Data Index: 132046 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3210. Min Act: -0.0001

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3358. Min Act: -0.0001

Data Index: 550157 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1284038 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3408. Min Act: -0.0000

Data Index: 851448 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1359607 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1054835 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.3091. Min Act: -0.0001

Data Index: 547037 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2942. Min Act: -0.0001

Data Index: 88096 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2911. Min Act: -0.0001

Data Index: 487217 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.4201. Min Range: -0.4201

Max Act: 0.2952. Min Act: -0.0001

Data Index: 233042 (C4 (Web Text))

Max Activating Token Index: 176