Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.6107. Min Act: -0.0001

Data Index: 1279711 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.6107. Min Range: -5.6107

Max Act: 5.0568. Min Act: -0.0001

Data Index: 977212 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.8991. Min Act: -0.0001

Data Index: 1218111 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.4072. Min Act: -0.0001

Data Index: 183438 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.4096. Min Act: -0.0001

Data Index: 1221094 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.5257. Min Act: -0.0001

Data Index: 1216834 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.4149. Min Act: -0.0001

Data Index: 1204393 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.3400. Min Act: 0.0001

Data Index: 1139244 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.2751. Min Act: -0.0001

Data Index: 855711 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.8089. Min Act: -0.0001

Data Index: 1156650 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 5.6107. Min Range: -5.6107

Max Act: 4.0562. Min Act: -0.0001

Data Index: 462238 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.7596. Min Act: -0.0000

Data Index: 995425 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.9279. Min Act: -0.0001

Data Index: 206442 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.8419. Min Act: -0.0000

Data Index: 406952 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.9766. Min Act: -0.0001

Data Index: 409777 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.7464. Min Act: -0.0001

Data Index: 185809 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.6002. Min Act: -0.0001

Data Index: 338780 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.3843. Min Act: -0.0001

Data Index: 739920 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.6689. Min Act: -0.0001

Data Index: 741176 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 5.6107. Min Range: -5.6107

Max Act: 3.6611. Min Act: -0.0001

Data Index: 558209 (C4 (Web Text))

Max Activating Token Index: 67