Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 164 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1068355 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.7200. Min Act: -0.1700
Data Index: 1522243 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6720. Min Act: -0.1700
Data Index: 1363085 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6399. Min Act: -0.1700
Data Index: 1395081 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6239. Min Act: -0.1700
Data Index: 1438444 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6239. Min Act: -0.1700
Data Index: 1609733 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1562537 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1495529 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.5917. Min Act: -0.1700
Data Index: 1577040 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1440982 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1488324 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1423130 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1652942 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1516422 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1655632 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1574849 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1656521 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.6078. Min Act: -0.1700
Data Index: 1551499 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.5917. Min Act: -0.1700
Data Index: 1541293 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7200. Min Range: -2.7200
Max Act: 2.5917. Min Act: -0.1700
Data Index: 1541300 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19