Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2965 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0004

Data Index: 1461226 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5342. Min Act: -0.0004

Data Index: 1527620 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5275. Min Act: -0.0004

Data Index: 1550621 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5238. Min Act: -0.0004

Data Index: 1567375 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5012. Min Act: -0.0004

Data Index: 1495240 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5198. Min Act: -0.0004

Data Index: 1365092 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4648. Min Act: -0.0004

Data Index: 1398656 (Python Code)

Max Activating Token Index: 116

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4713. Min Act: -0.0004

Data Index: 1420961 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4499. Min Act: -0.0004

Data Index: 1620418 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4525. Min Act: -0.0004

Data Index: 1657069 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4447. Min Act: -0.0004

Data Index: 1627700 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4841. Min Act: -0.0004

Data Index: 1569656 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4530. Min Act: -0.0004

Data Index: 1514806 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4332. Min Act: -0.0004

Data Index: 1416145 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4235. Min Act: -0.0004

Data Index: 1546969 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4324. Min Act: -0.0004

Data Index: 1510548 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4500. Min Act: -0.0004

Data Index: 1435638 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4331. Min Act: -0.0004

Data Index: 1502025 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4327. Min Act: -0.0004

Data Index: 1560795 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4041. Min Act: -0.0004

Data Index: 1380944 (Python Code)

Max Activating Token Index: 332