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

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

Neuron 124 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.7899. Min Act: -0.0001

Data Index: 343890 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.9724. Min Act: -0.0001

Data Index: 1304857 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.6999. Min Act: -0.0001

Data Index: 705292 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.6044. Min Act: -0.0001

Data Index: 1149804 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.6147. Min Act: -0.0001

Data Index: 958353 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.7019. Min Act: -0.0001

Data Index: 184414 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.5557. Min Act: -0.0001

Data Index: 640445 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.5626. Min Act: -0.0001

Data Index: 475144 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.5862. Min Act: -0.0001

Data Index: 262819 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.3810. Min Act: -0.0001

Data Index: 495591 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.4453. Min Act: -0.0001

Data Index: 791477 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.4339. Min Act: -0.0001

Data Index: 207236 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.1303. Min Act: -0.0001

Data Index: 656698 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.2839. Min Act: -0.0001

Data Index: 1266876 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.2741. Min Act: -0.0001

Data Index: 856426 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.3540. Min Act: -0.0001

Data Index: 668011 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.2559. Min Act: -0.0001

Data Index: 1169420 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.2766. Min Act: -0.0001

Data Index: 1102427 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.2579. Min Act: -0.0001

Data Index: 273327 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.9724. Min Range: -1.9724

Max Act: 1.3195. Min Act: -0.0001

Data Index: 1041992 (C4 (Web Text))

Max Activating Token Index: 696