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

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

Neuron 3948 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1246392 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1221610 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3302. Min Act: -0.0001

Data Index: 141165 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2894. Min Act: -0.0000

Data Index: 323904 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.3024. Min Act: -0.0000

Data Index: 595193 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2788. Min Act: -0.0000

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1353473 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2572. Min Act: -0.0000

Data Index: 294527 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1058253 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2460. Min Act: -0.0000

Data Index: 970959 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1141011 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2377. Min Act: -0.0000

Data Index: 885157 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2381. Min Act: -0.0001

Data Index: 250857 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2473. Min Act: -0.0000

Data Index: 202513 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1351204 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1174064 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2284. Min Act: -0.0000

Data Index: 377192 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2327. Min Act: -0.0001

Data Index: 123498 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2247. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.3738. Min Range: -0.3738

Max Act: 0.2084. Min Act: -0.0000

Data Index: 350635 (C4 (Web Text))

Max Activating Token Index: 387