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

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

Neuron 3622 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1535842 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1653955 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1369563 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1542375 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3921. Min Act: -0.0000

Data Index: 1494916 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3669. Min Act: -0.0000

Data Index: 1493109 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1477688 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1511939 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1437581 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1142040 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.6231. Min Range: -1.6231

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1505009 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1369696 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9985. Min Act: -0.0000

Data Index: 721320 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1510755 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9565. Min Act: -0.0000

Data Index: 871962 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1358368 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1385918 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9622. Min Act: -0.0000

Data Index: 366447 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1085563 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.6231. Min Range: -1.6231

Max Act: 0.8296. Min Act: -0.0000

Data Index: 112539 (C4 (Web Text))

Max Activating Token Index: 419