Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1408 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2900. Min Act: -0.1700

Data Index: 1578423 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.3082. Min Act: -0.1700

Data Index: 1593921 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.3158. Min Act: -0.1700

Data Index: 1502522 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2794. Min Act: -0.1700

Data Index: 1424045 (Python Code)

Max Activating Token Index: 183

Text #4

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2376. Min Act: -0.1700

Data Index: 1653039 (Python Code)

Max Activating Token Index: 949

Text #5

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2488. Min Act: -0.1700

Data Index: 1424272 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2522. Min Act: -0.1700

Data Index: 1422037 (Python Code)

Max Activating Token Index: 236

Text #7

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2250. Min Act: -0.1700

Data Index: 1599584 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2016. Min Act: -0.1699

Data Index: 1606489 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.2286. Min Act: -0.1700

Data Index: 1576106 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1789. Min Act: -0.1700

Data Index: 1575671 (Python Code)

Max Activating Token Index: 805

Text #11

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1571. Min Act: -0.1700

Data Index: 1638647 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1761. Min Act: -0.1700

Data Index: 1459278 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1052. Min Act: -0.1700

Data Index: 1417485 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1586. Min Act: -0.1700

Data Index: 1598697 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1651. Min Act: -0.1700

Data Index: 1640119 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1227. Min Act: -0.1700

Data Index: 1622204 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1099. Min Act: -0.1700

Data Index: 1384394 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1290. Min Act: -0.1700

Data Index: 1612855 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 4.3158. Min Range: -4.3158

Max Act: 4.1071. Min Act: -0.1700

Data Index: 1476492 (Python Code)

Max Activating Token Index: 921