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

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

Neuron 2044 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: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1100266 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1209. Min Act: -0.0001

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1206578 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1179. Min Act: -0.0001

Data Index: 10841 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1223. Min Act: -0.0001

Data Index: 885963 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1127. Min Act: -0.0001

Data Index: 221144 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1122651 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1116. Min Act: -0.0001

Data Index: 928286 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1021. Min Act: -0.0001

Data Index: 754200 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1098303 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1113. Min Act: -0.0001

Data Index: 43624 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1121429 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1268229 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1062. Min Act: -0.0001

Data Index: 7392 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0987. Min Act: -0.0001

Data Index: 737975 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1015. Min Act: -0.0001

Data Index: 252981 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0996. Min Act: -0.0001

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1172248 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1001. Min Act: -0.0001

Data Index: 991726 (C4 (Web Text))

Max Activating Token Index: 258