Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0607. Min Range: -1.0607

Max Act: 1.0607. Min Act: -0.0001

Data Index: 224974 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.7490. Min Act: -0.0001

Data Index: 282465 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6860. Min Act: -0.0001

Data Index: 400327 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6998. Min Act: -0.0001

Data Index: 526718 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6868. Min Act: -0.0001

Data Index: 1165411 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1032139 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6587. Min Act: -0.0001

Data Index: 76359 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6763. Min Act: -0.0001

Data Index: 126288 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1098613 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1082390 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6135. Min Act: -0.0001

Data Index: 592539 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6274. Min Act: -0.0001

Data Index: 763439 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6762. Min Act: -0.0001

Data Index: 85091 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6224. Min Act: -0.0001

Data Index: 391114 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.6225. Min Act: -0.0001

Data Index: 848474 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.5965. Min Act: -0.0001

Data Index: 314646 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.5674. Min Act: -0.0001

Data Index: 1190254 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.5854. Min Act: -0.0001

Data Index: 729913 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.0607. Min Range: -1.0607

Max Act: 0.5399. Min Act: -0.0001

Data Index: 431269 (C4 (Web Text))

Max Activating Token Index: 614