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

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

Neuron 4774 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5887. Min Act: -0.0000

Data Index: 86373 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1097843 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.0083. Min Act: -0.0000

Data Index: 64890 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.9739. Min Act: -0.0000

Data Index: 767034 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.9703. Min Act: -0.0000

Data Index: 403732 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1048581 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8748. Min Act: -0.0000

Data Index: 348957 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8996. Min Act: -0.0000

Data Index: 550188 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8749. Min Act: -0.0000

Data Index: 241930 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8570. Min Act: -0.0000

Data Index: 988 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8602. Min Act: -0.0000

Data Index: 94670 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1036020 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1081969 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8474. Min Act: -0.0000

Data Index: 259361 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.7479. Min Act: -0.0000

Data Index: 871679 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.8163. Min Act: -0.0000

Data Index: 37162 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.7641. Min Act: -0.0000

Data Index: 536377 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.7988. Min Act: -0.0000

Data Index: 616439 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.9137. Min Act: -0.0000

Data Index: 539634 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.5887. Min Range: -1.5887

Max Act: 0.7480. Min Act: -0.0000

Data Index: 811763 (C4 (Web Text))

Max Activating Token Index: 675