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

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

Neuron 3844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.7624. Min Act: -0.0000

Data Index: 764567 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.7992. Min Act: -0.0000

Data Index: 238057 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.4415. Min Act: -0.0000

Data Index: 875127 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1023790 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.6340. Min Act: -0.0000

Data Index: 163207 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.5643. Min Act: -0.0000

Data Index: 1301385 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.4870. Min Act: -0.0000

Data Index: 519143 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.5118. Min Act: -0.0000

Data Index: 795028 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1112030 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.3710. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.4426. Min Act: -0.0000

Data Index: 261541 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.3487. Min Act: -0.0000

Data Index: 517593 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.5301. Min Act: -0.0000

Data Index: 459148 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.3110. Min Act: -0.0000

Data Index: 366924 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.1876. Min Act: -0.0000

Data Index: 545803 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.3377. Min Act: -0.0000

Data Index: 733876 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.4221. Min Act: -0.0000

Data Index: 154036 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.2548. Min Act: -0.0000

Data Index: 228989 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.3239. Min Act: -0.0000

Data Index: 723314 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.7992. Min Range: -1.7992

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1324658 (C4 (Web Text))

Max Activating Token Index: 435