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

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

Neuron 4377 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: 1.8938. Min Range: -1.8938

Max Act: 1.8938. Min Act: -0.0000

Data Index: 440535 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.8390. Min Act: -0.0000

Data Index: 231754 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.8272. Min Act: -0.0000

Data Index: 168992 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1241582 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1008733 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7984. Min Act: -0.0000

Data Index: 473896 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6878. Min Act: -0.0000

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6527. Min Act: -0.0000

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.8392. Min Act: -0.0000

Data Index: 16593 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.5560. Min Act: -0.0000

Data Index: 580916 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7171. Min Act: -0.0000

Data Index: 526157 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7191. Min Act: -0.0000

Data Index: 163016 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6698. Min Act: -0.0000

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1004162 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6498. Min Act: -0.0000

Data Index: 114894 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.7321. Min Act: -0.0000

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.5279. Min Act: -0.0000

Data Index: 909455 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.8938. Min Range: -1.8938

Max Act: 1.6120. Min Act: -0.0000

Data Index: 724308 (C4 (Web Text))

Max Activating Token Index: 144