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

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

Neuron 2351 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: -0.0003

Data Index: 402531 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7574. Min Act: -0.0003

Data Index: 668329 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6702. Min Act: -0.0003

Data Index: 266444 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6959. Min Act: -0.0003

Data Index: 559115 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7078. Min Act: -0.0003

Data Index: 510669 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6793. Min Act: -0.0003

Data Index: 678861 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6278. Min Act: -0.0003

Data Index: 696875 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6667. Min Act: -0.0003

Data Index: 733840 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6367. Min Act: -0.0003

Data Index: 626404 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7029. Min Act: -0.0003

Data Index: 1128479 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7002. Min Act: -0.0003

Data Index: 50891 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6762. Min Act: -0.0003

Data Index: 366228 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6750. Min Act: -0.0003

Data Index: 1104372 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5856. Min Act: -0.0003

Data Index: 1282209 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6453. Min Act: -0.0003

Data Index: 485873 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6280. Min Act: -0.0003

Data Index: 1194931 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6873. Min Act: -0.0003

Data Index: 1245980 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6431. Min Act: -0.0003

Data Index: 4518 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6170. Min Act: -0.0003

Data Index: 1349103 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6165. Min Act: -0.0003

Data Index: 622194 (C4 (Web Text))

Max Activating Token Index: 675