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

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

Neuron 2040 in Layer 1

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: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1654440 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1402684 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1437350 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1477317 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1363458 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0002

Data Index: 119840 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1474162 (Python Code)

Max Activating Token Index: 229

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1517490 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1522060 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1520674 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1432977 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1576720 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1603492 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1547923 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0058. Min Act: -0.0002

Data Index: 675366 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1456881 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1378834 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1560609 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1401473 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1555132 (Python Code)

Max Activating Token Index: 199