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

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

Neuron 3965 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: 2.8465. Min Range: -2.8465

Max Act: 2.8264. Min Act: -0.0002

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.8465. Min Act: -0.0002

Data Index: 337221 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.8051. Min Act: -0.0002

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.7252. Min Act: -0.0003

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.6781. Min Act: -0.0002

Data Index: 1280096 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.6938. Min Act: -0.0002

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.6782. Min Act: -0.0002

Data Index: 1135276 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.7169. Min Act: -0.0002

Data Index: 612372 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.7015. Min Act: -0.0002

Data Index: 91381 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.6045. Min Act: -0.0002

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5522. Min Act: -0.0002

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5976. Min Act: -0.0002

Data Index: 591271 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5356. Min Act: -0.0002

Data Index: 1220657 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5011. Min Act: -0.0002

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.4646. Min Act: -0.0002

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5757. Min Act: -0.0003

Data Index: 862778 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.4598. Min Act: -0.0002

Data Index: 974776 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.4784. Min Act: -0.0002

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5619. Min Act: -0.0002

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 2.8465. Min Range: -2.8465

Max Act: 2.5008. Min Act: -0.0002

Data Index: 876467 (C4 (Web Text))

Max Activating Token Index: 251