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

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

Neuron 984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1113145 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2820. Min Act: -0.0000

Data Index: 127898 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2578. Min Act: -0.0000

Data Index: 347396 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2424. Min Act: -0.0000

Data Index: 147626 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2372. Min Act: -0.0000

Data Index: 360380 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1144478 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2481. Min Act: -0.0000

Data Index: 654303 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2311. Min Act: -0.0000

Data Index: 892213 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2463. Min Act: -0.0000

Data Index: 796452 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2248. Min Act: -0.0000

Data Index: 556863 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2199. Min Act: -0.0000

Data Index: 18803 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2423. Min Act: -0.0000

Data Index: 320914 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2098. Min Act: -0.0000

Data Index: 686832 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2083. Min Act: -0.0000

Data Index: 680628 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2269. Min Act: -0.0000

Data Index: 576075 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2158. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2299. Min Act: -0.0000

Data Index: 547830 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2065. Min Act: -0.0000

Data Index: 429406 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2062. Min Act: -0.0000

Data Index: 209149 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.4185. Min Range: -0.4185

Max Act: 0.2206. Min Act: -0.0000

Data Index: 702128 (C4 (Web Text))

Max Activating Token Index: 407