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

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

Neuron 2141 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: 1.7996. Min Range: -1.7996

Max Act: 1.7996. Min Act: -0.0001

Data Index: 164086 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.7239. Min Act: -0.0001

Data Index: 250876 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1275863 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.7500. Min Act: -0.0001

Data Index: 258129 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.5207. Min Act: -0.0001

Data Index: 868989 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4924. Min Act: -0.0001

Data Index: 937562 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4500. Min Act: -0.0001

Data Index: 582345 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.5122. Min Act: -0.0001

Data Index: 117957 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4215. Min Act: -0.0001

Data Index: 1256149 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4919. Min Act: -0.0001

Data Index: 212259 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4470. Min Act: -0.0001

Data Index: 26630 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.3952. Min Act: -0.0001

Data Index: 912064 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4064. Min Act: -0.0001

Data Index: 1137255 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4026. Min Act: -0.0001

Data Index: 207803 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4356. Min Act: -0.0001

Data Index: 577872 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4037. Min Act: -0.0001

Data Index: 250986 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.6227. Min Act: -0.0001

Data Index: 263492 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.3443. Min Act: -0.0001

Data Index: 1339398 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.4066. Min Act: -0.0001

Data Index: 116360 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.7996. Min Range: -1.7996

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1232090 (C4 (Web Text))

Max Activating Token Index: 850