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

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

Neuron 2805 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5922. Min Act: -0.0001

Data Index: 660099 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5520. Min Act: -0.0001

Data Index: 1310134 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5352. Min Act: -0.0001

Data Index: 1025600 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5158. Min Act: -0.0001

Data Index: 404469 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5130. Min Act: -0.0001

Data Index: 140889 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5238. Min Act: -0.0001

Data Index: 859852 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5154. Min Act: -0.0001

Data Index: 278924 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1086975 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5171. Min Act: -0.0001

Data Index: 1211572 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1122182 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4960. Min Act: -0.0001

Data Index: 7257 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5006. Min Act: -0.0001

Data Index: 529708 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1148662 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4956. Min Act: -0.0001

Data Index: 504523 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1053995 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4897. Min Act: -0.0001

Data Index: 286375 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4910. Min Act: -0.0001

Data Index: 1201163 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4853. Min Act: -0.0001

Data Index: 549888 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1188233 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.5922. Min Range: -0.5922

Max Act: 0.4918. Min Act: -0.0001

Data Index: 697155 (C4 (Web Text))

Max Activating Token Index: 13