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

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

Neuron 5701 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0001

Data Index: 6602 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3612. Min Act: -0.0001

Data Index: 379000 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3665. Min Act: -0.0001

Data Index: 853369 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3526. Min Act: -0.0001

Data Index: 1293285 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3336. Min Act: -0.0001

Data Index: 496839 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3139. Min Act: -0.0001

Data Index: 538433 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3467. Min Act: -0.0001

Data Index: 53352 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3078. Min Act: -0.0001

Data Index: 96841 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3360. Min Act: -0.0001

Data Index: 1178128 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3700. Min Act: -0.0001

Data Index: 918696 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3074. Min Act: -0.0001

Data Index: 178382 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1202066 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3197. Min Act: -0.0001

Data Index: 597408 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3085. Min Act: -0.0001

Data Index: 425222 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1051228 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1052397 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2907. Min Act: -0.0001

Data Index: 629916 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1199564 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3012. Min Act: -0.0001

Data Index: 653359 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3116. Min Act: -0.0001

Data Index: 357644 (C4 (Web Text))

Max Activating Token Index: 154