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

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

Neuron 3063 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: 0.3838. Min Range: -0.3838

Max Act: 0.3838. Min Act: -0.0001

Data Index: 699924 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3810. Min Act: -0.0001

Data Index: 920169 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3591. Min Act: -0.0001

Data Index: 1229242 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3538. Min Act: -0.0001

Data Index: 645163 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1100927 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3086. Min Act: -0.0001

Data Index: 97900 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3185. Min Act: -0.0000

Data Index: 248915 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1300846 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3291. Min Act: 0.0000

Data Index: 913008 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3111. Min Act: 0.0000

Data Index: 978559 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3001. Min Act: -0.0001

Data Index: 79738 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3117. Min Act: -0.0000

Data Index: 519109 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3017. Min Act: -0.0001

Data Index: 616252 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3005. Min Act: -0.0001

Data Index: 1231830 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3029. Min Act: -0.0001

Data Index: 556636 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.2972. Min Act: -0.0001

Data Index: 508994 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.2966. Min Act: -0.0001

Data Index: 786746 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.3167. Min Act: -0.0001

Data Index: 918061 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.2983. Min Act: -0.0000

Data Index: 245042 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.3838. Min Range: -0.3838

Max Act: 0.2916. Min Act: -0.0000

Data Index: 305205 (C4 (Web Text))

Max Activating Token Index: 768