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

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

Neuron 5728 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: 1.9961. Min Range: -1.9961

Max Act: 1.9961. Min Act: -0.0002

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.9659. Min Act: -0.0002

Data Index: 158356 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.9295. Min Act: -0.0003

Data Index: 356709 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.8861. Min Act: -0.0002

Data Index: 224383 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.8659. Min Act: -0.0002

Data Index: 387533 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.8487. Min Act: -0.0002

Data Index: 963494 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.8333. Min Act: -0.0003

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7804. Min Act: -0.0002

Data Index: 29721 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7623. Min Act: -0.0002

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7461. Min Act: -0.0002

Data Index: 359211 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7736. Min Act: -0.0002

Data Index: 1197294 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7135. Min Act: -0.0002

Data Index: 1122563 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7362. Min Act: -0.0002

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.6701. Min Act: -0.0002

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.6823. Min Act: -0.0003

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7041. Min Act: -0.0002

Data Index: 620559 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.7060. Min Act: -0.0002

Data Index: 171122 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.6443. Min Act: -0.0002

Data Index: 586815 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.6297. Min Act: -0.0003

Data Index: 336457 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.9961. Min Range: -1.9961

Max Act: 1.6443. Min Act: -0.0002

Data Index: 652271 (C4 (Web Text))

Max Activating Token Index: 119