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

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

Neuron 2089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4650. Min Act: -0.0001

Data Index: 941053 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4463. Min Act: -0.0001

Data Index: 793159 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1276507 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3161. Min Act: -0.0001

Data Index: 669957 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3478. Min Act: -0.0001

Data Index: 727916 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3763. Min Act: -0.0001

Data Index: 617652 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3612. Min Act: -0.0001

Data Index: 1220313 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2372. Min Act: -0.0001

Data Index: 558357 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3937. Min Act: -0.0001

Data Index: 8654 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2852. Min Act: -0.0001

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2980. Min Act: -0.0001

Data Index: 892977 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2973. Min Act: -0.0001

Data Index: 397280 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2644. Min Act: -0.0001

Data Index: 856565 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2312. Min Act: -0.0001

Data Index: 727620 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2642. Min Act: -0.0001

Data Index: 1207719 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2293. Min Act: -0.0001

Data Index: 428410 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1003563 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2748. Min Act: -0.0001

Data Index: 291232 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2812. Min Act: -0.0001

Data Index: 1328533 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2780. Min Act: -0.0001

Data Index: 117785 (C4 (Web Text))

Max Activating Token Index: 360