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

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

Neuron 3900 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: 1.5006. Min Range: -1.5006

Max Act: 1.4351. Min Act: -0.0001

Data Index: 1279821 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.5006. Min Act: -0.0001

Data Index: 276362 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.3314. Min Act: -0.0001

Data Index: 17148 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.4357. Min Act: -0.0001

Data Index: 1168014 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.3176. Min Act: -0.0001

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.3355. Min Act: -0.0001

Data Index: 428188 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.2686. Min Act: -0.0001

Data Index: 545141 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.2178. Min Act: -0.0001

Data Index: 536890 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.3241. Min Act: -0.0001

Data Index: 647015 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.2099. Min Act: -0.0001

Data Index: 237713 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1171. Min Act: -0.0001

Data Index: 369919 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1238. Min Act: -0.0001

Data Index: 819322 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.0931. Min Act: -0.0001

Data Index: 1178958 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1969. Min Act: -0.0001

Data Index: 899163 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.2098. Min Act: -0.0001

Data Index: 510112 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1780. Min Act: -0.0001

Data Index: 19825 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1508. Min Act: -0.0001

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 1.5006. Min Range: -1.5006

Max Act: 1.1493. Min Act: -0.0001

Data Index: 609323 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.5006. Min Range: -1.5006

Max Act: 0.9939. Min Act: -0.0001

Data Index: 441198 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.5006. Min Range: -1.5006

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1330055 (C4 (Web Text))

Max Activating Token Index: 117