Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 102 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.9753. Min Act: -0.1700
Data Index: 1458265 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.9278. Min Act: -0.1700
Data Index: 754813 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.9119. Min Act: -0.1700
Data Index: 1644952 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8961. Min Act: -0.1700
Data Index: 374898 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.9119. Min Act: -0.1700
Data Index: 1581155 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 750401 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8961. Min Act: -0.1700
Data Index: 743348 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 595824 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 236973 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8961. Min Act: -0.1700
Data Index: 1486511 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8484. Min Act: -0.1700
Data Index: 1382174 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8325. Min Act: -0.1700
Data Index: 1256283 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8484. Min Act: -0.1700
Data Index: 628140 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8325. Min Act: -0.1700
Data Index: 1391247 (Python Code)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 1572884 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8484. Min Act: -0.1700
Data Index: 1366982 (Python Code)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8484. Min Act: -0.1700
Data Index: 1392312 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8166. Min Act: -0.1700
Data Index: 1427780 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 1509785 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9753. Min Range: -2.9753
Max Act: 2.8643. Min Act: -0.1700
Data Index: 1644925 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19