Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.5835. Min Act: -0.0001

Data Index: 1348896 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.4924. Min Act: -0.0001

Data Index: 1126696 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.5590. Min Act: -0.0001

Data Index: 1207135 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.3694. Min Act: -0.0001

Data Index: 1189300 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.4497. Min Act: -0.0001

Data Index: 195108 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.0724. Min Act: -0.0001

Data Index: 684890 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.2900. Min Act: -0.0001

Data Index: 1335170 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.2818. Min Act: -0.0001

Data Index: 1182478 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.2755. Min Act: -0.0001

Data Index: 170311 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.2573. Min Act: -0.0001

Data Index: 441578 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.1736. Min Act: -0.0001

Data Index: 494210 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.1419. Min Act: -0.0001

Data Index: 1049993 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.1132. Min Act: -0.0001

Data Index: 716094 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.0007. Min Act: -0.0001

Data Index: 483278 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.0992. Min Act: -0.0001

Data Index: 475597 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.5835. Min Range: -2.5835

Max Act: 1.9597. Min Act: -0.0001

Data Index: 948585 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.5835. Min Range: -2.5835

Max Act: 1.8105. Min Act: -0.0001

Data Index: 293660 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 2.5835. Min Range: -2.5835

Max Act: 1.9674. Min Act: -0.0001

Data Index: 628507 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.5835. Min Range: -2.5835

Max Act: 2.0025. Min Act: -0.0001

Data Index: 251248 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.5835. Min Range: -2.5835

Max Act: 1.9496. Min Act: -0.0001

Data Index: 628355 (C4 (Web Text))

Max Activating Token Index: 633