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

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

Neuron 661 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: 1.0446. Min Range: -1.0446

Max Act: 1.0446. Min Act: -0.0002

Data Index: 1249431 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.0446. Min Range: -1.0446

Max Act: 1.0139. Min Act: -0.0002

Data Index: 941595 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9771. Min Act: -0.0002

Data Index: 469452 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9942. Min Act: -0.0002

Data Index: 447789 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9798. Min Act: -0.0002

Data Index: 402981 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9583. Min Act: -0.0002

Data Index: 488510 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9324. Min Act: -0.0002

Data Index: 998633 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9447. Min Act: -0.0002

Data Index: 654893 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9487. Min Act: -0.0002

Data Index: 462112 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9215. Min Act: -0.0002

Data Index: 1272836 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9161. Min Act: -0.0002

Data Index: 1068627 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9248. Min Act: -0.0002

Data Index: 857335 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9318. Min Act: -0.0002

Data Index: 686505 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9284. Min Act: -0.0002

Data Index: 341563 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9191. Min Act: -0.0002

Data Index: 929905 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9357. Min Act: -0.0002

Data Index: 826328 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9086. Min Act: -0.0002

Data Index: 757873 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9094. Min Act: -0.0002

Data Index: 78466 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9144. Min Act: -0.0002

Data Index: 1209371 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.0446. Min Range: -1.0446

Max Act: 0.9027. Min Act: -0.0002

Data Index: 1119902 (C4 (Web Text))

Max Activating Token Index: 109