Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2146. Min Range: -1.2146

Max Act: 1.0899. Min Act: -0.0001

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 1.2146. Min Range: -1.2146

Max Act: 1.2146. Min Act: -0.0001

Data Index: 849938 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.2146. Min Range: -1.2146

Max Act: 1.0148. Min Act: -0.0001

Data Index: 254972 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9740. Min Act: -0.0001

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9684. Min Act: -0.0001

Data Index: 39904 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9861. Min Act: -0.0001

Data Index: 894409 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9493. Min Act: -0.0001

Data Index: 40427 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1320558 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9735. Min Act: -0.0001

Data Index: 613675 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9043. Min Act: -0.0001

Data Index: 983101 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8388. Min Act: -0.0001

Data Index: 608647 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8793. Min Act: -0.0001

Data Index: 434485 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8516. Min Act: -0.0001

Data Index: 888219 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.9195. Min Act: -0.0001

Data Index: 221558 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8816. Min Act: -0.0001

Data Index: 11132 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8590. Min Act: -0.0001

Data Index: 1131481 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8000. Min Act: -0.0001

Data Index: 591354 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8202. Min Act: -0.0001

Data Index: 906460 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.8215. Min Act: -0.0001

Data Index: 972961 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.2146. Min Range: -1.2146

Max Act: 0.7938. Min Act: -0.0001

Data Index: 969689 (C4 (Web Text))

Max Activating Token Index: 836