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

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

Neuron 3480 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6734. Min Act: -0.0002

Data Index: 235985 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6739. Min Act: -0.0002

Data Index: 39286 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6964. Min Act: -0.0002

Data Index: 488640 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6912. Min Act: -0.0002

Data Index: 1070050 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6320. Min Act: -0.0002

Data Index: 1215912 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5970. Min Act: -0.0002

Data Index: 1024308 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5639. Min Act: -0.0002

Data Index: 362957 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5464. Min Act: -0.0002

Data Index: 266512 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5398. Min Act: -0.0002

Data Index: 189620 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5466. Min Act: -0.0002

Data Index: 1285428 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5669. Min Act: -0.0002

Data Index: 687951 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5353. Min Act: -0.0002

Data Index: 186253 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5343. Min Act: -0.0002

Data Index: 1207446 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5330. Min Act: -0.0002

Data Index: 1232977 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5403. Min Act: -0.0002

Data Index: 321487 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5722. Min Act: -0.0002

Data Index: 1252997 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5151. Min Act: -0.0002

Data Index: 178298 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5148. Min Act: -0.0002

Data Index: 6587 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4843. Min Act: -0.0002

Data Index: 517173 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5084. Min Act: -0.0002

Data Index: 538262 (C4 (Web Text))

Max Activating Token Index: 407