Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2146 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1552629 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 393058 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1194481 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1335028 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 705112 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 889241 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1558623 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 629131 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1597616 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 648314 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 340059 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1182090 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1433147 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0002

Data Index: 122478 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1048387 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1312174 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0002

Data Index: 61715 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 720456 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1116828 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1226288 (C4 (Web Text))

Max Activating Token Index: 459