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

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

Neuron 2820 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: 0.1381. Min Range: -0.1381

Max Act: 0.1381. Min Act: -0.0001

Data Index: 711400 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1200. Min Act: -0.0001

Data Index: 921537 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1154. Min Act: -0.0001

Data Index: 830748 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1152. Min Act: -0.0001

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1110. Min Act: -0.0001

Data Index: 730582 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1037257 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1010. Min Act: -0.0001

Data Index: 135235 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0984. Min Act: -0.0001

Data Index: 354627 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1236171 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.1006. Min Act: -0.0001

Data Index: 42787 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1123834 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0953. Min Act: -0.0001

Data Index: 512044 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0935. Min Act: -0.0001

Data Index: 704057 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1061304 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1077725 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0949. Min Act: -0.0001

Data Index: 950170 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0942. Min Act: -0.0001

Data Index: 777472 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0918. Min Act: -0.0001

Data Index: 169884 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0907. Min Act: -0.0001

Data Index: 164232 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.1381. Min Range: -0.1381

Max Act: 0.0910. Min Act: -0.0001

Data Index: 175337 (C4 (Web Text))

Max Activating Token Index: 358