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

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

Neuron 43 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: 1.4163. Min Range: -1.4163

Max Act: 1.4163. Min Act: -0.0002

Data Index: 890489 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.4117. Min Act: -0.0002

Data Index: 1187505 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3754. Min Act: -0.0002

Data Index: 118835 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3684. Min Act: -0.0002

Data Index: 369147 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3731. Min Act: -0.0002

Data Index: 787746 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3673. Min Act: -0.0002

Data Index: 1151200 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3568. Min Act: -0.0002

Data Index: 276792 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3583. Min Act: -0.0002

Data Index: 308138 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3472. Min Act: -0.0002

Data Index: 130419 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.3233. Min Act: -0.0002

Data Index: 821708 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2859. Min Act: -0.0002

Data Index: 819428 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2736. Min Act: -0.0002

Data Index: 1054268 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2646. Min Act: -0.0002

Data Index: 1081994 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2922. Min Act: -0.0002

Data Index: 851748 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2501. Min Act: -0.0002

Data Index: 375142 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2662. Min Act: -0.0002

Data Index: 516012 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2671. Min Act: -0.0002

Data Index: 108651 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2362. Min Act: -0.0002

Data Index: 199764 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2663. Min Act: -0.0002

Data Index: 75968 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.4163. Min Range: -1.4163

Max Act: 1.2288. Min Act: -0.0002

Data Index: 714486 (C4 (Web Text))

Max Activating Token Index: 4