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

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

Neuron 1243 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8332. Min Act: -0.0000

Data Index: 617780 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7995. Min Act: -0.0000

Data Index: 477159 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1647181 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1379252 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8609. Min Act: -0.0001

Data Index: 1446238 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1020003 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1621316 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1389603 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1474604 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1388913 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1555680 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1621619 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1544374 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1536633 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1375100 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1529422 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1514725 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1652565 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1185057 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1425678 (Python Code)

Max Activating Token Index: 92