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

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

Neuron 3971 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1332173 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1746. Min Act: -0.0001

Data Index: 589290 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1658. Min Act: -0.0001

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1543. Min Act: -0.0001

Data Index: 4574 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1538. Min Act: -0.0001

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1428. Min Act: -0.0001

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1353. Min Act: -0.0001

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1365. Min Act: -0.0001

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1496. Min Act: -0.0001

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1338. Min Act: -0.0001

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1261827 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1359. Min Act: -0.0001

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1327. Min Act: -0.0001

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1258. Min Act: -0.0001

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1272. Min Act: -0.0001

Data Index: 98817 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1363. Min Act: -0.0001

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1314. Min Act: -0.0001

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 28