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

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

Neuron 6049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.7050. Min Act: -0.0001

Data Index: 1511445 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.8946. Min Act: -0.0001

Data Index: 1588288 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.8172. Min Act: -0.0001

Data Index: 1435073 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.5042. Min Act: -0.0001

Data Index: 1182039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.6705. Min Act: -0.0001

Data Index: 1445754 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.3424. Min Act: -0.0001

Data Index: 1525471 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.4599. Min Act: -0.0001

Data Index: 1590061 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.5378. Min Act: -0.0001

Data Index: 1616147 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.6806. Min Act: -0.0001

Data Index: 1598224 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.4227. Min Act: -0.0001

Data Index: 1407168 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.2718. Min Act: -0.0001

Data Index: 1464094 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.2952. Min Act: -0.0001

Data Index: 1569859 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.3220. Min Act: -0.0001

Data Index: 1519455 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.2313. Min Act: -0.0001

Data Index: 1553338 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.0922. Min Act: -0.0001

Data Index: 1177231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.0428. Min Act: -0.0001

Data Index: 1455364 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.1676. Min Act: -0.0001

Data Index: 1361633 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.0951. Min Act: -0.0001

Data Index: 1637430 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 14.8946. Min Range: -14.8946

Max Act: 14.1328. Min Act: -0.0001

Data Index: 1616086 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 14.8946. Min Range: -14.8946

Max Act: 13.9046. Min Act: -0.0001

Data Index: 1602655 (Python Code)

Max Activating Token Index: 1023