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

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

Neuron 4897 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.1389. Min Act: -0.0000

Data Index: 903306 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.0157. Min Act: 0.0000

Data Index: 156745 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9976. Min Act: -0.0000

Data Index: 741283 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1252046 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9329. Min Act: -0.0000

Data Index: 964749 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8682. Min Act: -0.0000

Data Index: 938295 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8306. Min Act: -0.0000

Data Index: 445392 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1125453 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1296924 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6353. Min Act: -0.0000

Data Index: 510565 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6234. Min Act: -0.0000

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6336. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5697. Min Act: -0.0000

Data Index: 945893 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5632. Min Act: -0.0000

Data Index: 900167 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5523. Min Act: -0.0000

Data Index: 623296 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5458. Min Act: -0.0000

Data Index: 318480 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1071364 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.4959. Min Act: -0.0000

Data Index: 548128 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.5285. Min Act: -0.0000

Data Index: 149010 (C4 (Web Text))

Max Activating Token Index: 711