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

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

Neuron 2748 in Layer 1

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: 0.4795. Min Range: -0.4795

Max Act: 0.4795. Min Act: -0.0002

Data Index: 688848 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4315. Min Act: -0.0002

Data Index: 53305 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4249. Min Act: -0.0002

Data Index: 727091 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4138. Min Act: -0.0002

Data Index: 712353 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4162. Min Act: -0.0003

Data Index: 1184583 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4166. Min Act: -0.0002

Data Index: 61751 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4074. Min Act: -0.0002

Data Index: 1356685 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3992. Min Act: -0.0002

Data Index: 1070570 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4029. Min Act: -0.0002

Data Index: 495853 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4039. Min Act: -0.0002

Data Index: 197558 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4045. Min Act: -0.0002

Data Index: 1057092 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3956. Min Act: -0.0002

Data Index: 51120 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3986. Min Act: -0.0002

Data Index: 896841 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3969. Min Act: -0.0002

Data Index: 205406 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3921. Min Act: -0.0002

Data Index: 756021 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3946. Min Act: -0.0002

Data Index: 1208 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3916. Min Act: -0.0002

Data Index: 1202942 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3905. Min Act: -0.0002

Data Index: 623456 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3908. Min Act: -0.0002

Data Index: 860803 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3899. Min Act: -0.0002

Data Index: 234380 (C4 (Web Text))

Max Activating Token Index: 63