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

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

Neuron 3444 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: 4.0400. Min Range: -4.0400

Max Act: 4.0400. Min Act: -0.0000

Data Index: 586797 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.7903. Min Act: -0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.9764. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4922. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.7972. Min Act: -0.0000

Data Index: 326640 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.6091. Min Act: -0.0000

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4354. Min Act: -0.0000

Data Index: 1305368 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4873. Min Act: -0.0000

Data Index: 689217 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.3687. Min Act: -0.0000

Data Index: 814591 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.1954. Min Act: -0.0000

Data Index: 114306 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.3198. Min Act: -0.0000

Data Index: 124397 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1277693 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4608. Min Act: -0.0000

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.4778. Min Act: -0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.2705. Min Act: -0.0001

Data Index: 892187 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.8957. Min Act: -0.0000

Data Index: 1100437 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 4.0400. Min Range: -4.0400

Max Act: 3.0552. Min Act: -0.0000

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.5264. Min Act: -0.0000

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.9166. Min Act: -0.0001

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 4.0400. Min Range: -4.0400

Max Act: 2.9284. Min Act: -0.0000

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 640