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

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

Neuron 3610 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: 2.2460. Min Range: -2.2460

Max Act: 2.2460. Min Act: -0.0000

Data Index: 212671 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0112. Min Act: -0.0001

Data Index: 825283 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0086. Min Act: -0.0000

Data Index: 639427 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.9215. Min Act: 0.0004

Data Index: 196937 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8523. Min Act: 0.0004

Data Index: 385972 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7477. Min Act: -0.0000

Data Index: 312402 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8068. Min Act: -0.0000

Data Index: 1133411 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7671. Min Act: -0.0001

Data Index: 1330056 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7728. Min Act: 0.0006

Data Index: 1182768 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1073806 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8114. Min Act: -0.0000

Data Index: 365283 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.6555. Min Act: 0.0001

Data Index: 137005 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.6587. Min Act: -0.0001

Data Index: 290919 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.6038. Min Act: 0.0003

Data Index: 481743 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5541. Min Act: -0.0000

Data Index: 115949 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1176416 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5290. Min Act: 0.0001

Data Index: 669258 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5214. Min Act: -0.0000

Data Index: 967522 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5148. Min Act: -0.0001

Data Index: 449549 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1173251 (C4 (Web Text))

Max Activating Token Index: 431