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

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

Neuron 1848 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0001

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0379. Min Act: -0.0001

Data Index: 337667 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1272831 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0332. Min Act: -0.0001

Data Index: 316550 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1196057 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0315. Min Act: -0.0001

Data Index: 845719 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0336. Min Act: -0.0000

Data Index: 402154 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0305. Min Act: -0.0001

Data Index: 722480 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0325. Min Act: -0.0001

Data Index: 445997 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1172318 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0306. Min Act: -0.0001

Data Index: 260099 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0293. Min Act: -0.0001

Data Index: 620215 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1224606 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1294507 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0288. Min Act: -0.0001

Data Index: 198778 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1556256 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0268. Min Act: -0.0001

Data Index: 274551 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0274. Min Act: -0.0001

Data Index: 78427 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1328434 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0281. Min Act: -0.0001

Data Index: 257995 (C4 (Web Text))

Max Activating Token Index: 190