Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1476640 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1651338 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1594744 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1518846 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1488134 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1479054 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3431. Min Act: -0.0001

Data Index: 1628832 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1482090 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3532. Min Act: -0.0001

Data Index: 1617492 (Python Code)

Max Activating Token Index: 618

Text #9

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1495553 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3290. Min Act: -0.0001

Data Index: 182232 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3163. Min Act: -0.0001

Data Index: 1486517 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1574207 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1645455 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1447351 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1525500 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.2797. Min Act: -0.0001

Data Index: 973610 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3428. Min Act: -0.0001

Data Index: 471019 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1593164 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3189. Min Act: -0.0001

Data Index: 1538340 (Python Code)

Max Activating Token Index: 732