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

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

Neuron 2506 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2933. Min Range: -1.2933

Max Act: 1.2933. Min Act: -0.0000

Data Index: 449199 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.2933. Min Range: -1.2933

Max Act: 1.2396. Min Act: -0.0000

Data Index: 359314 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 1.2933. Min Range: -1.2933

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.2933. Min Range: -1.2933

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1147807 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.6951. Min Act: -0.0000

Data Index: 287399 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.5740. Min Act: -0.0000

Data Index: 474310 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.5135. Min Act: -0.0000

Data Index: 818826 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.5023. Min Act: -0.0000

Data Index: 227151 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1286207 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4753. Min Act: -0.0000

Data Index: 176634 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.5008. Min Act: -0.0000

Data Index: 313301 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.5020. Min Act: -0.0000

Data Index: 792091 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4593. Min Act: -0.0000

Data Index: 634752 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1493692 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4434. Min Act: -0.0000

Data Index: 900458 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4369. Min Act: -0.0000

Data Index: 148612 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4101. Min Act: -0.0000

Data Index: 973107 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1307397 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.2933. Min Range: -1.2933

Max Act: 0.4480. Min Act: -0.0000

Data Index: 870547 (C4 (Web Text))

Max Activating Token Index: 100