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

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

Neuron 4737 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.5890. Min Act: -0.0002

Data Index: 379054 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4939. Min Act: -0.0002

Data Index: 959801 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4698. Min Act: -0.0002

Data Index: 924921 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4816. Min Act: -0.0002

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4552. Min Act: -0.0002

Data Index: 213210 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4089. Min Act: -0.0002

Data Index: 152226 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4272. Min Act: -0.0002

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4465. Min Act: -0.0002

Data Index: 942945 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4746. Min Act: -0.0002

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4374. Min Act: -0.0002

Data Index: 1336984 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4709. Min Act: -0.0002

Data Index: 1298782 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4492. Min Act: -0.0002

Data Index: 1256644 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4359. Min Act: -0.0002

Data Index: 119182 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4301. Min Act: -0.0002

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4276. Min Act: -0.0002

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.4067. Min Act: -0.0002

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3911. Min Act: -0.0002

Data Index: 951349 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3880. Min Act: -0.0002

Data Index: 276742 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3682. Min Act: -0.0002

Data Index: 1191544 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3872. Min Act: -0.0002

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 623