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

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

Neuron 203 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4978. Min Act: -0.0002

Data Index: 920394 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4808. Min Act: -0.0002

Data Index: 135316 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4453. Min Act: -0.0002

Data Index: 665506 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4539. Min Act: -0.0002

Data Index: 530947 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4414. Min Act: -0.0002

Data Index: 1331967 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4177. Min Act: -0.0003

Data Index: 39823 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4229. Min Act: -0.0003

Data Index: 1118630 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4290. Min Act: -0.0002

Data Index: 95047 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4223. Min Act: -0.0002

Data Index: 1162007 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4101. Min Act: -0.0003

Data Index: 1324733 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4145. Min Act: -0.0002

Data Index: 975042 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4067. Min Act: -0.0002

Data Index: 415528 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4010. Min Act: -0.0002

Data Index: 900473 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4185. Min Act: -0.0002

Data Index: 878758 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3934. Min Act: -0.0002

Data Index: 1280381 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3965. Min Act: -0.0002

Data Index: 1217504 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3874. Min Act: -0.0002

Data Index: 127434 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3908. Min Act: -0.0002

Data Index: 752757 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3785. Min Act: -0.0002

Data Index: 668537 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3942. Min Act: -0.0002

Data Index: 592704 (C4 (Web Text))

Max Activating Token Index: 173