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

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

Neuron 2085 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: 0.5405. Min Range: -0.5405

Max Act: 0.5405. Min Act: -0.0002

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5333. Min Act: -0.0002

Data Index: 759213 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5188. Min Act: -0.0002

Data Index: 1041342 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4879. Min Act: -0.0002

Data Index: 1074735 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4876. Min Act: -0.0002

Data Index: 273575 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4901. Min Act: -0.0002

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4728. Min Act: -0.0002

Data Index: 405283 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4720. Min Act: -0.0002

Data Index: 520747 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4707. Min Act: -0.0002

Data Index: 543829 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4584. Min Act: -0.0002

Data Index: 1209034 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4598. Min Act: -0.0002

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4537. Min Act: -0.0002

Data Index: 388472 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4563. Min Act: -0.0002

Data Index: 382261 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4501. Min Act: -0.0002

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4493. Min Act: -0.0002

Data Index: 675569 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4588. Min Act: -0.0002

Data Index: 17135 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4492. Min Act: -0.0002

Data Index: 1138625 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4558. Min Act: -0.0002

Data Index: 869057 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4554. Min Act: -0.0002

Data Index: 385640 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4503. Min Act: -0.0002

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 904