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

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

Neuron 4625 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: 1.0464. Min Range: -1.0464

Max Act: 1.0442. Min Act: -0.0001

Data Index: 521171 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.0464. Min Range: -1.0464

Max Act: 1.0464. Min Act: -0.0001

Data Index: 1073562 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.0464. Min Range: -1.0464

Max Act: 1.0235. Min Act: -0.0001

Data Index: 18177 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9917. Min Act: -0.0001

Data Index: 624145 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9472. Min Act: -0.0001

Data Index: 76291 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1253037 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9230. Min Act: -0.0001

Data Index: 332967 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9036. Min Act: -0.0001

Data Index: 428452 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9101. Min Act: -0.0001

Data Index: 919196 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9021. Min Act: -0.0001

Data Index: 380523 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.9026. Min Act: -0.0001

Data Index: 53444 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8731. Min Act: -0.0002

Data Index: 1187261 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8866. Min Act: -0.0001

Data Index: 701780 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8824. Min Act: -0.0001

Data Index: 1344214 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1017573 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1630204 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8751. Min Act: -0.0001

Data Index: 1167388 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8504. Min Act: -0.0001

Data Index: 994854 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8648. Min Act: -0.0001

Data Index: 732201 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.0464. Min Range: -1.0464

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1140359 (C4 (Web Text))

Max Activating Token Index: 116