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

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

Neuron 2167 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: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0002

Data Index: 1538529 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7534. Min Act: -0.0002

Data Index: 1601427 (Python Code)

Max Activating Token Index: 750

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.7130. Min Act: -0.0002

Data Index: 1056679 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6853. Min Act: -0.0002

Data Index: 707762 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6554. Min Act: -0.0002

Data Index: 1109758 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6602. Min Act: -0.0002

Data Index: 903146 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6509. Min Act: -0.0002

Data Index: 65286 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6370. Min Act: -0.0002

Data Index: 570341 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6130. Min Act: -0.0002

Data Index: 176139 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6335. Min Act: -0.0002

Data Index: 1376737 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6272. Min Act: -0.0002

Data Index: 1596004 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6290. Min Act: -0.0002

Data Index: 537778 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6139. Min Act: -0.0002

Data Index: 763518 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6126. Min Act: -0.0002

Data Index: 76431 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6129. Min Act: -0.0002

Data Index: 74225 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5981. Min Act: -0.0002

Data Index: 1394294 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6023. Min Act: -0.0002

Data Index: 402702 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5952. Min Act: -0.0002

Data Index: 416076 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5866. Min Act: -0.0002

Data Index: 589596 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5847. Min Act: -0.0002

Data Index: 186768 (C4 (Web Text))

Max Activating Token Index: 89