Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3996 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1448113 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1586389 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2784. Min Act: -0.0001

Data Index: 1461211 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2951. Min Act: -0.0001

Data Index: 1379913 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1466823 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1611670 (Python Code)

Max Activating Token Index: 640

Text #6

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1484956 (Python Code)

Max Activating Token Index: 692

Text #7

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1113914 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2387. Min Act: -0.0001

Data Index: 279546 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1440027 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1655938 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2429. Min Act: -0.0001

Data Index: 1434513 (Python Code)

Max Activating Token Index: 582

Text #12

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1396378 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2253. Min Act: -0.0001

Data Index: 1446839 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1408091 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1380349 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2141. Min Act: -0.0001

Data Index: 1609511 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1483558 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2351. Min Act: -0.0001

Data Index: 900880 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1253518 (C4 (Web Text))

Max Activating Token Index: 481