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

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

Neuron 5946 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.9277. Min Act: -0.0002

Data Index: 836885 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.9090. Min Act: -0.0002

Data Index: 929139 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8960. Min Act: -0.0002

Data Index: 1488539 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8639. Min Act: -0.0002

Data Index: 600251 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8794. Min Act: -0.0002

Data Index: 685729 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8535. Min Act: -0.0002

Data Index: 284071 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8438. Min Act: -0.0002

Data Index: 1186766 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8469. Min Act: -0.0002

Data Index: 1033202 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8361. Min Act: -0.0002

Data Index: 919228 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8426. Min Act: -0.0002

Data Index: 799620 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8384. Min Act: -0.0002

Data Index: 197057 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8191. Min Act: -0.0002

Data Index: 245958 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8191. Min Act: -0.0002

Data Index: 538684 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8266. Min Act: -0.0002

Data Index: 1237983 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8395. Min Act: -0.0002

Data Index: 392288 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8090. Min Act: -0.0002

Data Index: 1162197 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8083. Min Act: -0.0002

Data Index: 717547 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8044. Min Act: -0.0002

Data Index: 990877 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8015. Min Act: -0.0002

Data Index: 343147 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.9277. Min Range: -0.9277

Max Act: 0.8057. Min Act: -0.0002

Data Index: 231461 (C4 (Web Text))

Max Activating Token Index: 159