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

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

Neuron 5457 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.9137. Min Act: 0.0000

Data Index: 1071549 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8506. Min Act: -0.0000

Data Index: 225372 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8443. Min Act: -0.0000

Data Index: 898348 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7855. Min Act: 0.0000

Data Index: 820381 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8253. Min Act: -0.0000

Data Index: 337177 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7711. Min Act: -0.0000

Data Index: 168546 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7071. Min Act: -0.0000

Data Index: 511949 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7088. Min Act: -0.0000

Data Index: 640961 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6941. Min Act: -0.0000

Data Index: 244036 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1296522 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6723. Min Act: -0.0000

Data Index: 106414 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7117. Min Act: 0.0001

Data Index: 1011955 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7120. Min Act: -0.0000

Data Index: 782968 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6950. Min Act: 0.0001

Data Index: 334320 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6864. Min Act: -0.0000

Data Index: 422679 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1271095 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1321581 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6945. Min Act: 0.0000

Data Index: 844347 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6922. Min Act: 0.0001

Data Index: 1320819 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6604. Min Act: 0.0000

Data Index: 1045679 (C4 (Web Text))

Max Activating Token Index: 602