Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 264 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.2611. Min Act: -0.1700
Data Index: 1573962 (Python Code)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1586529 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1673. Min Act: -0.1700
Data Index: 1543687 (Python Code)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1048. Min Act: -0.1700
Data Index: 1635043 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1399489 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1475782 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0735. Min Act: -0.1700
Data Index: 1585245 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1599012 (Python Code)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1588361 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0735. Min Act: -0.1700
Data Index: 1366967 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1600719 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1366679 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0110. Min Act: -0.1700
Data Index: 1555042 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1493844 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1598461 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1540757 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0735. Min Act: -0.1700
Data Index: 1463725 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1507025 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0423. Min Act: -0.1700
Data Index: 1550845 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2611. Min Range: -4.2611
Max Act: 4.0110. Min Act: -0.1700
Data Index: 1616568 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19