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

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

Neuron 2347 in Layer 0

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: 0.4951. Min Range: -0.4951

Max Act: 0.4951. Min Act: -0.0001

Data Index: 1309720 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4705. Min Act: -0.0001

Data Index: 946187 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4596. Min Act: -0.0001

Data Index: 649953 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4715. Min Act: -0.0001

Data Index: 979818 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4687. Min Act: -0.0001

Data Index: 191264 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4685. Min Act: -0.0001

Data Index: 513487 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4584. Min Act: -0.0001

Data Index: 1073627 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4581. Min Act: -0.0001

Data Index: 530876 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4598. Min Act: -0.0001

Data Index: 472045 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1132133 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4544. Min Act: -0.0001

Data Index: 683780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4540. Min Act: -0.0001

Data Index: 916663 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4600. Min Act: -0.0001

Data Index: 642755 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4526. Min Act: -0.0002

Data Index: 127646 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4606. Min Act: -0.0001

Data Index: 849681 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4598. Min Act: -0.0001

Data Index: 571432 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4606. Min Act: -0.0001

Data Index: 166750 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4487. Min Act: -0.0001

Data Index: 50433 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4496. Min Act: -0.0001

Data Index: 131297 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4487. Min Act: -0.0001

Data Index: 654935 (C4 (Web Text))

Max Activating Token Index: 350