Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3636 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.8682. Min Act: -0.0001

Data Index: 212167 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7598. Min Act: -0.0001

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7534. Min Act: -0.0001

Data Index: 608419 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7545. Min Act: -0.0001

Data Index: 36903 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7497. Min Act: -0.0001

Data Index: 1068963 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7507. Min Act: -0.0001

Data Index: 200969 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7347. Min Act: -0.0001

Data Index: 816066 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7416. Min Act: -0.0001

Data Index: 1280110 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7427. Min Act: -0.0002

Data Index: 580860 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7387. Min Act: -0.0001

Data Index: 551345 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7378. Min Act: -0.0001

Data Index: 425964 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1166656 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1256301 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7338. Min Act: -0.0002

Data Index: 23322 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7287. Min Act: -0.0001

Data Index: 1113561 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7114. Min Act: -0.0001

Data Index: 779440 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1102908 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7091. Min Act: -0.0001

Data Index: 706084 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7089. Min Act: -0.0001

Data Index: 943161 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.8682. Min Range: -0.8682

Max Act: 0.7064. Min Act: -0.0001

Data Index: 591807 (C4 (Web Text))

Max Activating Token Index: 49