Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1523138 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1374711 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1520825 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1433257 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1379487 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1655554 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1375135 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1488457 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1628434 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1546752 (Python Code)

Max Activating Token Index: 259

Text #10

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0940. Min Act: 0.0001

Data Index: 1529967 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1523362 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1435998 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1605742 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1543140 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1360966 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0881. Min Act: 0.0001

Data Index: 1539520 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1646888 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1510217 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1412936 (Python Code)

Max Activating Token Index: 108