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

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

Neuron 925 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: 3.5774. Min Range: -3.5774

Max Act: 3.5697. Min Act: -0.1700

Data Index: 1525840 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.5774. Min Act: -0.1699

Data Index: 1360792 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.5413. Min Act: -0.1699

Data Index: 1427557 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.5181. Min Act: -0.1699

Data Index: 1594282 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1611922 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4565. Min Act: -0.1700

Data Index: 1643160 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4566. Min Act: -0.1699

Data Index: 1421583 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4225. Min Act: -0.1700

Data Index: 1401695 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4066. Min Act: -0.1700

Data Index: 1652954 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4065. Min Act: -0.1699

Data Index: 1418977 (Python Code)

Max Activating Token Index: 415

Text #10

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4034. Min Act: -0.1698

Data Index: 1446813 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3949. Min Act: -0.1700

Data Index: 1646145 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4016. Min Act: -0.1700

Data Index: 1624267 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.4068. Min Act: -0.1699

Data Index: 1576027 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3905. Min Act: -0.1700

Data Index: 1433813 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1593922 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3713. Min Act: -0.1700

Data Index: 1481675 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3606. Min Act: -0.1700

Data Index: 1641935 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3461. Min Act: -0.1699

Data Index: 1366817 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 3.5774. Min Range: -3.5774

Max Act: 3.3535. Min Act: -0.1700

Data Index: 1378601 (Python Code)

Max Activating Token Index: 893