Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 100 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.7951. Min Act: -0.1678
Data Index: 1594282 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.6673. Min Act: -0.1700
Data Index: 287332 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.4576. Min Act: -0.1699
Data Index: 1580619 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.4414. Min Act: -0.1700
Data Index: 1647608 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.4414. Min Act: -0.1699
Data Index: 1383563 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.4414. Min Act: -0.1698
Data Index: 1568790 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.3925. Min Act: -0.1700
Data Index: 1498571 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.3434. Min Act: -0.1700
Data Index: 1507289 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.3434. Min Act: -0.1700
Data Index: 1411055 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.3434. Min Act: -0.1700
Data Index: 1393097 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.3106. Min Act: -0.1700
Data Index: 1618384 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.2447. Min Act: -0.1699
Data Index: 1582930 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.2447. Min Act: -0.1700
Data Index: 1611563 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.2116. Min Act: -0.1700
Data Index: 1612305 (Python Code)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1951. Min Act: -0.1694
Data Index: 1601532 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1785. Min Act: -0.1699
Data Index: 1466871 (Python Code)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1618. Min Act: -0.1700
Data Index: 1644308 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1452. Min Act: -0.1700
Data Index: 1627988 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1535. Min Act: -0.1700
Data Index: 1643805 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7951. Min Range: -2.7951
Max Act: 2.1452. Min Act: -0.1700
Data Index: 1557991 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19