Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1154 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1321049 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.5155. Min Act: -0.0000

Data Index: 364079 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3995. Min Act: -0.0000

Data Index: 437596 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3845. Min Act: -0.0000

Data Index: 888293 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3413. Min Act: -0.0001

Data Index: 466585 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3436. Min Act: -0.0000

Data Index: 472546 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3435. Min Act: -0.0001

Data Index: 1419814 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3308. Min Act: -0.0000

Data Index: 218 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3542. Min Act: -0.0000

Data Index: 239251 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3046. Min Act: -0.0001

Data Index: 882742 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1337947 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2973. Min Act: -0.0001

Data Index: 1530085 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3288. Min Act: -0.0000

Data Index: 154851 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3050. Min Act: -0.0000

Data Index: 710625 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3246. Min Act: -0.0000

Data Index: 698505 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.3212. Min Act: -0.0000

Data Index: 570111 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2990. Min Act: -0.0000

Data Index: 304648 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1218324 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2951. Min Act: -0.0001

Data Index: 625147 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.5332. Min Range: -0.5332

Max Act: 0.2889. Min Act: -0.0000

Data Index: 626270 (C4 (Web Text))

Max Activating Token Index: 20