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

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

Neuron 465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4769. Min Act: -0.0001

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4806. Min Act: -0.0001

Data Index: 14900 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4195. Min Act: -0.0001

Data Index: 464174 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1036830 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4418. Min Act: -0.0001

Data Index: 248868 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4568. Min Act: -0.0001

Data Index: 59448 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4223. Min Act: -0.0001

Data Index: 358620 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1335325 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4285. Min Act: -0.0001

Data Index: 1340879 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4309. Min Act: -0.0001

Data Index: 866795 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1046586 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4220. Min Act: -0.0001

Data Index: 519125 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4095. Min Act: -0.0001

Data Index: 51112 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4087. Min Act: -0.0001

Data Index: 1111790 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4475. Min Act: -0.0001

Data Index: 179278 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4173. Min Act: -0.0001

Data Index: 394670 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4131. Min Act: -0.0001

Data Index: 632828 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.4140. Min Act: -0.0001

Data Index: 44168 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.5154. Min Range: -0.5154

Max Act: 0.3833. Min Act: -0.0001

Data Index: 143924 (C4 (Web Text))

Max Activating Token Index: 815