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

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

Neuron 26 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.1958. Min Act: -0.0001

Data Index: 450144 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0764. Min Act: -0.0001

Data Index: 946053 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0565. Min Act: -0.0001

Data Index: 494169 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.1054. Min Act: -0.0001

Data Index: 278262 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.1009. Min Act: -0.0001

Data Index: 65623 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0546. Min Act: -0.0001

Data Index: 742059 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8408. Min Act: -0.0002

Data Index: 562720 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0530. Min Act: -0.0001

Data Index: 479087 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1264926 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9429. Min Act: -0.0001

Data Index: 911246 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0073. Min Act: -0.0001

Data Index: 849160 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0515. Min Act: -0.0001

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9553. Min Act: -0.0001

Data Index: 48335 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1050549 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0213. Min Act: -0.0001

Data Index: 230010 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0008. Min Act: -0.0001

Data Index: 1305516 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.8774. Min Act: -0.0001

Data Index: 471676 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0209. Min Act: -0.0001

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.1958. Min Range: -1.1958

Max Act: 1.0042. Min Act: -0.0001

Data Index: 108603 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 1.1958. Min Range: -1.1958

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1106418 (C4 (Web Text))

Max Activating Token Index: 72