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

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

Neuron 4756 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: 0.9764. Min Range: -0.9764

Max Act: 0.9764. Min Act: -0.0002

Data Index: 1301394 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9170. Min Act: -0.0002

Data Index: 864922 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8997. Min Act: -0.0002

Data Index: 472157 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9096. Min Act: -0.0002

Data Index: 692109 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8826. Min Act: -0.0002

Data Index: 646913 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9081. Min Act: -0.0002

Data Index: 777446 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8991. Min Act: -0.0002

Data Index: 1254835 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8879. Min Act: -0.0002

Data Index: 379198 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8802. Min Act: -0.0002

Data Index: 1349558 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8868. Min Act: -0.0002

Data Index: 1291891 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8541. Min Act: -0.0002

Data Index: 754147 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8515. Min Act: -0.0002

Data Index: 78135 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8491. Min Act: -0.0002

Data Index: 289139 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8795. Min Act: -0.0002

Data Index: 359379 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8673. Min Act: -0.0002

Data Index: 685248 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8546. Min Act: -0.0002

Data Index: 255954 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8384. Min Act: -0.0002

Data Index: 698686 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8602. Min Act: -0.0002

Data Index: 823327 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8487. Min Act: -0.0002

Data Index: 435128 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8307. Min Act: -0.0002

Data Index: 974215 (C4 (Web Text))

Max Activating Token Index: 374