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

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

Neuron 2467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0307. Min Range: -1.0307

Max Act: 1.0307. Min Act: -0.0001

Data Index: 497401 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.9255. Min Act: -0.0001

Data Index: 205467 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8896. Min Act: -0.0001

Data Index: 186192 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8618. Min Act: -0.0001

Data Index: 1081881 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8146. Min Act: -0.0001

Data Index: 285555 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7643. Min Act: -0.0001

Data Index: 367857 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8741. Min Act: -0.0001

Data Index: 1168901 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.0307. Min Range: -1.0307

Max Act: 1.0085. Min Act: -0.0001

Data Index: 40767 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1228822 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8302. Min Act: -0.0000

Data Index: 397031 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7758. Min Act: -0.0001

Data Index: 421493 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8449. Min Act: -0.0001

Data Index: 433283 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7993. Min Act: -0.0001

Data Index: 167970 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1134646 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7986. Min Act: -0.0001

Data Index: 840216 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8168. Min Act: -0.0001

Data Index: 652324 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8063. Min Act: -0.0001

Data Index: 101083 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7625. Min Act: -0.0001

Data Index: 322940 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.8093. Min Act: -0.0000

Data Index: 889065 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.0307. Min Range: -1.0307

Max Act: 0.7566. Min Act: -0.0001

Data Index: 832394 (C4 (Web Text))

Max Activating Token Index: 181