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

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

Neuron 2404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.5121. Min Act: -0.0000

Data Index: 925390 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1092500 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4691. Min Act: -0.0000

Data Index: 150481 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1316002 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4576. Min Act: -0.0000

Data Index: 783695 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1257194 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4446. Min Act: -0.0000

Data Index: 18935 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4446. Min Act: -0.0000

Data Index: 902308 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4302. Min Act: -0.0000

Data Index: 405238 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4300. Min Act: -0.0000

Data Index: 595226 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4177. Min Act: -0.0000

Data Index: 837467 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4174. Min Act: -0.0000

Data Index: 727308 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4260. Min Act: -0.0000

Data Index: 719038 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4248. Min Act: -0.0000

Data Index: 969163 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4240. Min Act: -0.0000

Data Index: 646159 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4246. Min Act: -0.0000

Data Index: 978039 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4368. Min Act: -0.0000

Data Index: 338860 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4208. Min Act: -0.0000

Data Index: 439525 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4194. Min Act: -0.0000

Data Index: 735480 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4197. Min Act: -0.0000

Data Index: 652545 (C4 (Web Text))

Max Activating Token Index: 114