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

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

Neuron 1747 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: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0001

Data Index: 891123 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0072. Min Act: -0.0001

Data Index: 197243 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1119401 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1248120 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1598479 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1169244 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0001

Data Index: 262877 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1118259 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0001

Data Index: 421981 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0001

Data Index: 488394 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1559105 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0001

Data Index: 625070 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0002

Data Index: 523106 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0001

Data Index: 691384 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0001

Data Index: 1577283 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1272583 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0001

Data Index: 444153 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1121368 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1056633 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0001

Data Index: 1041835 (C4 (Web Text))

Max Activating Token Index: 77