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

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

Neuron 1138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.5104. Min Act: -0.0001

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1140196 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4370. Min Act: -0.0001

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4637. Min Act: -0.0001

Data Index: 137489 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4401. Min Act: -0.0001

Data Index: 640124 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4531. Min Act: -0.0001

Data Index: 719107 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4224. Min Act: -0.0001

Data Index: 930264 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4211. Min Act: -0.0001

Data Index: 485938 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4154. Min Act: -0.0001

Data Index: 286198 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4022. Min Act: -0.0001

Data Index: 575648 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4125. Min Act: -0.0001

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4132. Min Act: -0.0001

Data Index: 885367 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.3860. Min Act: -0.0001

Data Index: 609999 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4250. Min Act: -0.0001

Data Index: 487462 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4414. Min Act: -0.0001

Data Index: 36526 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.3857. Min Act: -0.0001

Data Index: 222481 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4009. Min Act: -0.0001

Data Index: 841839 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4135. Min Act: -0.0001

Data Index: 538578 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1333271 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.5104. Min Range: -0.5104

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1005040 (C4 (Web Text))

Max Activating Token Index: 320