Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.4521. Min Act: -0.0000

Data Index: 71919 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.6076. Min Act: -0.0000

Data Index: 143442 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.7134. Min Act: -0.0001

Data Index: 243725 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.5743. Min Act: -0.0000

Data Index: 1178844 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.4148. Min Act: -0.0001

Data Index: 633601 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.3970. Min Act: -0.0000

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2383. Min Act: -0.0000

Data Index: 707649 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.3098. Min Act: -0.0000

Data Index: 256805 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1216. Min Act: -0.0001

Data Index: 219841 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1052. Min Act: -0.0000

Data Index: 408428 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2484. Min Act: -0.0000

Data Index: 798537 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2598. Min Act: -0.0000

Data Index: 430183 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.0965. Min Act: -0.0000

Data Index: 116935 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2225. Min Act: -0.0000

Data Index: 415880 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2443. Min Act: -0.0001

Data Index: 611758 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2165. Min Act: -0.0000

Data Index: 1013561 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1922. Min Act: -0.0000

Data Index: 1196288 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.3158. Min Act: -0.0001

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1671. Min Act: -0.0001

Data Index: 629234 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 3.7134. Min Range: -3.7134

Max Act: 2.9728. Min Act: -0.0000

Data Index: 871965 (C4 (Web Text))

Max Activating Token Index: 132