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

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

Neuron 2050 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: 1.9800. Min Range: -1.9800

Max Act: 1.9800. Min Act: -0.0001

Data Index: 1448214 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.9515. Min Act: -0.0001

Data Index: 1360435 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.9543. Min Act: -0.0001

Data Index: 1386857 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.8500. Min Act: -0.0001

Data Index: 1428339 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.7408. Min Act: -0.0001

Data Index: 1470840 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.8204. Min Act: -0.0001

Data Index: 1474982 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.7170. Min Act: -0.0001

Data Index: 1622831 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.7274. Min Act: -0.0001

Data Index: 1621472 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.7203. Min Act: -0.0001

Data Index: 1533055 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6163. Min Act: -0.0001

Data Index: 1408187 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6305. Min Act: -0.0001

Data Index: 1589610 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6458. Min Act: -0.0001

Data Index: 1430986 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6319. Min Act: -0.0001

Data Index: 1504909 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.7130. Min Act: -0.0001

Data Index: 1469567 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6482. Min Act: -0.0001

Data Index: 1576347 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.5559. Min Act: -0.0001

Data Index: 1535259 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.5740. Min Act: -0.0001

Data Index: 1446572 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.6468. Min Act: -0.0001

Data Index: 1522629 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.5516. Min Act: -0.0001

Data Index: 1581208 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 1.9800. Min Range: -1.9800

Max Act: 1.5442. Min Act: -0.0001

Data Index: 1379086 (Python Code)

Max Activating Token Index: 36