Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.4127. Min Act: -0.0000

Data Index: 109971 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1066536 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3437. Min Act: -0.0000

Data Index: 982739 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3391. Min Act: -0.0000

Data Index: 559226 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3267. Min Act: -0.0000

Data Index: 63216 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3257. Min Act: -0.0000

Data Index: 834938 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3093. Min Act: -0.0000

Data Index: 26047 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1098781 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1038988 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3094. Min Act: -0.0000

Data Index: 654285 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2894. Min Act: -0.0000

Data Index: 220407 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3079. Min Act: -0.0000

Data Index: 325810 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3092. Min Act: -0.0000

Data Index: 713144 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.3159. Min Act: -0.0000

Data Index: 190894 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2985. Min Act: -0.0000

Data Index: 321432 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1168260 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1295332 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1043089 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2928. Min Act: -0.0000

Data Index: 321668 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.4127. Min Range: -0.4127

Max Act: 0.2899. Min Act: -0.0000

Data Index: 562771 (C4 (Web Text))

Max Activating Token Index: 915