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

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

Neuron 2796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.3325. Min Act: -0.0001

Data Index: 80098 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.4154. Min Act: -0.0001

Data Index: 1208682 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.3081. Min Act: -0.0001

Data Index: 1258092 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.2935. Min Act: -0.0001

Data Index: 947476 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.2128. Min Act: -0.0001

Data Index: 161588 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.1896. Min Act: -0.0001

Data Index: 231929 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.0681. Min Act: -0.0001

Data Index: 1201800 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9883. Min Act: -0.0001

Data Index: 672673 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.0256. Min Act: -0.0001

Data Index: 654028 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.4154. Min Range: -1.4154

Max Act: 1.0698. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9870. Min Act: -0.0001

Data Index: 826146 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9976. Min Act: -0.0001

Data Index: 1219804 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9890. Min Act: -0.0000

Data Index: 373517 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9605. Min Act: -0.0001

Data Index: 53556 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1339771 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1251496 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9116. Min Act: -0.0001

Data Index: 680235 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9168. Min Act: -0.0001

Data Index: 404823 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9232. Min Act: -0.0001

Data Index: 714451 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.4154. Min Range: -1.4154

Max Act: 0.9609. Min Act: -0.0001

Data Index: 1180250 (C4 (Web Text))

Max Activating Token Index: 687