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

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

Neuron 750 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: 1.1395. Min Range: -1.1395

Max Act: 1.1395. Min Act: -0.0001

Data Index: 741508 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.1395. Min Range: -1.1395

Max Act: 1.0434. Min Act: -0.0001

Data Index: 595919 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.1395. Min Range: -1.1395

Max Act: 1.0270. Min Act: -0.0001

Data Index: 71412 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.1395. Min Range: -1.1395

Max Act: 1.0330. Min Act: -0.0001

Data Index: 1008739 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.1395. Min Range: -1.1395

Max Act: 1.0083. Min Act: -0.0001

Data Index: 866790 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.1395. Min Range: -1.1395

Max Act: 1.0040. Min Act: -0.0001

Data Index: 298731 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9902. Min Act: -0.0001

Data Index: 1258956 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9685. Min Act: -0.0001

Data Index: 531598 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9642. Min Act: -0.0001

Data Index: 409044 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9691. Min Act: -0.0001

Data Index: 610508 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9554. Min Act: -0.0001

Data Index: 406925 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9347. Min Act: -0.0001

Data Index: 603130 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9586. Min Act: -0.0001

Data Index: 482884 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9437. Min Act: -0.0001

Data Index: 203177 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9492. Min Act: -0.0001

Data Index: 1129875 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9441. Min Act: -0.0001

Data Index: 157064 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9233. Min Act: -0.0001

Data Index: 1032693 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9495. Min Act: -0.0001

Data Index: 675148 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9565. Min Act: -0.0001

Data Index: 688393 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.1395. Min Range: -1.1395

Max Act: 0.9321. Min Act: -0.0001

Data Index: 413735 (C4 (Web Text))

Max Activating Token Index: 10