Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 567 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0006

Data Index: 698900 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1264998 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 317186 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 3810 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1314981 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 427949 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1173724 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 877635 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 850301 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1056210 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0005

Data Index: 11593 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 170400 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 993565 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 562440 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 787837 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 716182 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1282607 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1090168 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1087126 (C4 (Web Text))

Max Activating Token Index: 211