Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1005 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.4314. Min Act: -0.1700
Data Index: 1411795 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.2126. Min Act: -0.1700
Data Index: 1073350 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.1814. Min Act: -0.1700
Data Index: 1468717 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.1189. Min Act: -0.1700
Data Index: 272992 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.1501. Min Act: -0.1700
Data Index: 1648398 (Python Code)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0563. Min Act: -0.1700
Data Index: 1454070 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0563. Min Act: -0.1700
Data Index: 1217726 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0563. Min Act: -0.1700
Data Index: 810850 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0563. Min Act: -0.1700
Data Index: 250302 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0251. Min Act: -0.1700
Data Index: 1387866 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9938. Min Act: -0.1700
Data Index: 1456804 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1462736 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0563. Min Act: -0.1700
Data Index: 1517054 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0251. Min Act: -0.1700
Data Index: 142299 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9938. Min Act: -0.1700
Data Index: 1261865 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9938. Min Act: -0.1700
Data Index: 104142 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9313. Min Act: -0.1700
Data Index: 1472706 (Python Code)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0251. Min Act: -0.1700
Data Index: 1481743 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4314. Min Range: -4.4314
Max Act: 3.9938. Min Act: -0.1700
Data Index: 1509258 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4314. Min Range: -4.4314
Max Act: 4.0251. Min Act: -0.1700
Data Index: 434864 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19