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

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

Neuron 5728 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1206160 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1490822 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1471758 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4456. Min Act: -0.0000

Data Index: 377460 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1253153 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4441. Min Act: -0.0000

Data Index: 300474 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4155. Min Act: -0.0000

Data Index: 78844 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4078. Min Act: -0.0000

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4088. Min Act: -0.0000

Data Index: 40724 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4374. Min Act: -0.0000

Data Index: 572403 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4302. Min Act: -0.0000

Data Index: 447409 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1151238 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4133. Min Act: -0.0000

Data Index: 338097 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3984. Min Act: -0.0000

Data Index: 661439 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4098. Min Act: -0.0000

Data Index: 668023 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3994. Min Act: -0.0000

Data Index: 254175 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4098. Min Act: -0.0000

Data Index: 695811 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3929. Min Act: -0.0000

Data Index: 318074 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3677. Min Act: -0.0000

Data Index: 505001 (C4 (Web Text))

Max Activating Token Index: 648