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

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

Neuron 3557 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4477. Min Act: -0.0001

Data Index: 319148 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4380. Min Act: -0.0001

Data Index: 704956 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4330. Min Act: -0.0001

Data Index: 697559 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4148. Min Act: -0.0001

Data Index: 367037 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4110. Min Act: -0.0001

Data Index: 428455 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4093. Min Act: -0.0001

Data Index: 363197 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4142. Min Act: -0.0001

Data Index: 287327 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4038. Min Act: -0.0001

Data Index: 921552 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4097. Min Act: -0.0001

Data Index: 398284 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4063. Min Act: -0.0002

Data Index: 867954 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1155597 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3964. Min Act: -0.0001

Data Index: 252969 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3932. Min Act: -0.0001

Data Index: 475347 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1052722 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4056. Min Act: -0.0001

Data Index: 197558 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.4037. Min Act: -0.0001

Data Index: 884876 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3902. Min Act: -0.0001

Data Index: 858069 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3869. Min Act: -0.0001

Data Index: 468268 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3837. Min Act: -0.0001

Data Index: 923250 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.4477. Min Range: -0.4477

Max Act: 0.3814. Min Act: -0.0001

Data Index: 1242386 (C4 (Web Text))

Max Activating Token Index: 518