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

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

Neuron 513 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4913. Min Act: -0.0000

Data Index: 657993 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4684. Min Act: -0.0000

Data Index: 718465 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4453. Min Act: -0.0000

Data Index: 1237082 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1213692 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4104. Min Act: -0.0000

Data Index: 1121412 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1192348 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3529. Min Act: -0.0000

Data Index: 629476 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3330. Min Act: -0.0000

Data Index: 867545 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.4335. Min Act: -0.0000

Data Index: 1317870 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3080. Min Act: -0.0000

Data Index: 588095 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.1748. Min Act: -0.0000

Data Index: 245068 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.1708. Min Act: -0.0000

Data Index: 1146990 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3781. Min Act: -0.0000

Data Index: 268157 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.1471. Min Act: -0.0000

Data Index: 1327592 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.0787. Min Act: -0.0000

Data Index: 377552 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3256. Min Act: -0.0000

Data Index: 980280 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.2158. Min Act: -0.0000

Data Index: 442479 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3109. Min Act: -0.0000

Data Index: 33542 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 2.4913. Min Range: -2.4913

Max Act: 1.9726. Min Act: -0.0000

Data Index: 971977 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.4913. Min Range: -2.4913

Max Act: 2.3662. Min Act: -0.0000

Data Index: 519209 (C4 (Web Text))

Max Activating Token Index: 874