Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 935 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1276. Min Act: -0.0003

Data Index: 873139 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1197. Min Act: -0.0003

Data Index: 164791 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1212. Min Act: -0.0003

Data Index: 1133935 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1171. Min Act: -0.0003

Data Index: 705 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1144. Min Act: -0.0003

Data Index: 303302 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1104. Min Act: -0.0003

Data Index: 956850 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1101. Min Act: -0.0003

Data Index: 457908 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1043. Min Act: -0.0003

Data Index: 320817 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1000020 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1178. Min Act: -0.0003

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1085. Min Act: -0.0004

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1096. Min Act: -0.0003

Data Index: 220428 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1074. Min Act: -0.0003

Data Index: 1091839 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1060. Min Act: -0.0003

Data Index: 781098 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1067. Min Act: -0.0003

Data Index: 760000 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1101. Min Act: -0.0003

Data Index: 271030 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1057. Min Act: -0.0004

Data Index: 756279 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0983. Min Act: -0.0003

Data Index: 530617 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1041. Min Act: -0.0003

Data Index: 48472 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1148323 (C4 (Web Text))

Max Activating Token Index: 47