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

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

Neuron 2340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4180. Min Act: -0.0001

Data Index: 831088 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4301. Min Act: -0.0000

Data Index: 693084 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4097. Min Act: -0.0000

Data Index: 34388 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1142851 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3629. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3710. Min Act: -0.0001

Data Index: 233056 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3475. Min Act: -0.0001

Data Index: 763202 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3456. Min Act: -0.0000

Data Index: 682020 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1045080 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3323. Min Act: -0.0001

Data Index: 388274 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3572. Min Act: -0.0000

Data Index: 628629 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3430. Min Act: -0.0001

Data Index: 950721 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3417. Min Act: -0.0001

Data Index: 285708 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3359. Min Act: -0.0000

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1211092 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3347. Min Act: -0.0000

Data Index: 630168 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3463. Min Act: -0.0000

Data Index: 920037 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3242. Min Act: -0.0001

Data Index: 831282 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1302427 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3326. Min Act: -0.0001

Data Index: 753492 (C4 (Web Text))

Max Activating Token Index: 77