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

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

Neuron 2814 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4862. Min Act: -0.0000

Data Index: 597637 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4312. Min Act: -0.0000

Data Index: 414250 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4147. Min Act: -0.0000

Data Index: 273064 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4306. Min Act: -0.0000

Data Index: 511624 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3861. Min Act: -0.0000

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4190. Min Act: -0.0000

Data Index: 524276 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4025. Min Act: -0.0000

Data Index: 295485 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1021071 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3745. Min Act: -0.0000

Data Index: 419064 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4136. Min Act: -0.0000

Data Index: 957168 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3805. Min Act: -0.0000

Data Index: 398739 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3918. Min Act: -0.0000

Data Index: 457820 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3792. Min Act: -0.0000

Data Index: 232800 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1182061 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3881. Min Act: -0.0000

Data Index: 905531 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3629. Min Act: -0.0000

Data Index: 524742 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3477. Min Act: -0.0000

Data Index: 397486 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1218215 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3656. Min Act: -0.0000

Data Index: 450590 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3645. Min Act: -0.0000

Data Index: 204249 (C4 (Web Text))

Max Activating Token Index: 82