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

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

Neuron 1108 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1602580 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4836. Min Act: -0.0000

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4929. Min Act: -0.0000

Data Index: 491284 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.5070. Min Act: -0.0000

Data Index: 583893 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1045289 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1488191 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1166221 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1069413 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4549. Min Act: -0.0000

Data Index: 327937 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1105828 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1253692 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1555437 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4510. Min Act: -0.0000

Data Index: 673272 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1455950 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4439. Min Act: -0.0000

Data Index: 2488 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4357. Min Act: -0.0000

Data Index: 222111 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1266400 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4239. Min Act: -0.0000

Data Index: 70883 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.4160. Min Act: -0.0000

Data Index: 737594 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.5296. Min Range: -0.5296

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1276328 (C4 (Web Text))

Max Activating Token Index: 877