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

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

Neuron 4351 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1545272 (Python Code)

Max Activating Token Index: 750

Text #1

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2872. Min Act: -0.0000

Data Index: 802168 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.3344. Min Act: -0.0000

Data Index: 288460 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1468551 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1469917 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1372032 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1274732 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1156539 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1633379 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0942. Min Act: -0.0000

Data Index: 390014 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1565989 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1554116 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9003. Min Act: -0.0000

Data Index: 625943 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1394232 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1376959 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1455492 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1624749 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.8831. Min Act: -0.0000

Data Index: 353057 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9191. Min Act: -0.0000

Data Index: 698346 (C4 (Web Text))

Max Activating Token Index: 408