Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4146. Min Act: -0.0001

Data Index: 36778 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3672. Min Act: -0.0001

Data Index: 268385 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3638. Min Act: -0.0001

Data Index: 638108 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3348. Min Act: -0.0001

Data Index: 879808 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2933. Min Act: -0.0001

Data Index: 1060842 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2798. Min Act: -0.0000

Data Index: 791352 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2730. Min Act: -0.0001

Data Index: 334118 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2929. Min Act: -0.0000

Data Index: 998666 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1231440 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2847. Min Act: -0.0001

Data Index: 423992 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2743. Min Act: -0.0001

Data Index: 171691 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2594. Min Act: -0.0000

Data Index: 930450 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2593. Min Act: -0.0001

Data Index: 581590 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2611. Min Act: -0.0000

Data Index: 68724 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2513. Min Act: -0.0000

Data Index: 341215 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2473. Min Act: -0.0001

Data Index: 762429 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2642. Min Act: -0.0000

Data Index: 64473 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2450. Min Act: -0.0001

Data Index: 882000 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1271782 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2558. Min Act: -0.0001

Data Index: 380360 (C4 (Web Text))

Max Activating Token Index: 572