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

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

Neuron 5716 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4277. Min Act: -0.0001

Data Index: 1356092 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4284. Min Act: -0.0001

Data Index: 208598 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4059. Min Act: -0.0001

Data Index: 927016 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4035. Min Act: -0.0001

Data Index: 254973 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3606. Min Act: -0.0001

Data Index: 234809 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3495. Min Act: -0.0001

Data Index: 1256056 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3699. Min Act: -0.0001

Data Index: 947282 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3634. Min Act: -0.0001

Data Index: 1204641 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3156. Min Act: -0.0001

Data Index: 484670 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3016. Min Act: -0.0001

Data Index: 896748 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1122856 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3376. Min Act: -0.0001

Data Index: 701147 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3244. Min Act: -0.0001

Data Index: 484957 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3069. Min Act: -0.0001

Data Index: 117008 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1187855 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1067706 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3088. Min Act: -0.0001

Data Index: 384413 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2975. Min Act: -0.0001

Data Index: 519525 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2961. Min Act: -0.0001

Data Index: 288497 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2881. Min Act: -0.0001

Data Index: 491943 (C4 (Web Text))

Max Activating Token Index: 638