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

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

Neuron 5313 in Layer 1

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: 1.6209. Min Range: -1.6209

Max Act: 1.6209. Min Act: -0.0002

Data Index: 291091 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5815. Min Act: -0.0002

Data Index: 1178032 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5576. Min Act: -0.0002

Data Index: 658587 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4980. Min Act: -0.0002

Data Index: 889913 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4814. Min Act: -0.0002

Data Index: 613115 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4631. Min Act: -0.0002

Data Index: 618558 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4492. Min Act: -0.0002

Data Index: 382074 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4102. Min Act: -0.0003

Data Index: 1220271 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3879. Min Act: -0.0003

Data Index: 1296859 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4314. Min Act: -0.0002

Data Index: 1268768 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4057. Min Act: -0.0002

Data Index: 1127108 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4254. Min Act: -0.0002

Data Index: 788201 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4080. Min Act: -0.0002

Data Index: 1180622 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3911. Min Act: -0.0002

Data Index: 792167 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3830. Min Act: -0.0002

Data Index: 923328 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3997. Min Act: -0.0002

Data Index: 1359580 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4052. Min Act: -0.0002

Data Index: 361597 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3860. Min Act: -0.0002

Data Index: 949892 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3781. Min Act: -0.0002

Data Index: 437513 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3893. Min Act: -0.0002

Data Index: 18067 (C4 (Web Text))

Max Activating Token Index: 288