Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2318 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5864. Min Act: -0.0001

Data Index: 984905 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6404. Min Act: -0.0001

Data Index: 937911 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.6012. Min Act: -0.0001

Data Index: 1630616 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.3954. Min Act: -0.0001

Data Index: 1535887 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5228. Min Act: -0.0001

Data Index: 1556489 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.5097. Min Act: -0.0001

Data Index: 695069 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4612. Min Act: -0.0001

Data Index: 1619457 (Python Code)

Max Activating Token Index: 262

Text #7

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4714. Min Act: -0.0001

Data Index: 1429698 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1632809 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4598. Min Act: -0.0001

Data Index: 709591 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4630. Min Act: -0.0001

Data Index: 1420577 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.3661. Min Act: -0.0001

Data Index: 1522678 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4898. Min Act: -0.0001

Data Index: 1402409 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4126. Min Act: -0.0001

Data Index: 1475905 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4347. Min Act: -0.0001

Data Index: 1405602 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4357. Min Act: -0.0001

Data Index: 1530779 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.3945. Min Act: -0.0001

Data Index: 1548284 (Python Code)

Max Activating Token Index: 136

Text #17

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4302. Min Act: -0.0001

Data Index: 1582184 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4270. Min Act: -0.0001

Data Index: 1518413 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 1.6404. Min Range: -1.6404

Max Act: 1.4671. Min Act: -0.0001

Data Index: 1430500 (Python Code)

Max Activating Token Index: 90