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

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

Neuron 3517 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0144. Min Range: -1.0144

Max Act: 1.0144. Min Act: -0.0001

Data Index: 354774 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6988. Min Act: -0.0001

Data Index: 494098 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.7067. Min Act: -0.0001

Data Index: 1264490 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6746. Min Act: -0.0001

Data Index: 876756 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6405. Min Act: -0.0001

Data Index: 2170 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6547. Min Act: -0.0001

Data Index: 320659 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6245. Min Act: -0.0001

Data Index: 383238 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1079855 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6296. Min Act: -0.0001

Data Index: 668606 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5963. Min Act: -0.0001

Data Index: 438665 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6159. Min Act: -0.0001

Data Index: 904945 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5933. Min Act: -0.0001

Data Index: 1144279 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6016. Min Act: -0.0001

Data Index: 934520 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6020. Min Act: -0.0001

Data Index: 391575 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5744. Min Act: -0.0001

Data Index: 128097 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6191. Min Act: -0.0001

Data Index: 1047186 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.6114. Min Act: -0.0001

Data Index: 920006 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5800. Min Act: -0.0001

Data Index: 956630 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5545. Min Act: -0.0001

Data Index: 5252 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.0144. Min Range: -1.0144

Max Act: 0.5641. Min Act: -0.0001

Data Index: 436584 (C4 (Web Text))

Max Activating Token Index: 405