Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2034 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1859. Min Range: -4.1859
Max Act: 4.1859. Min Act: -0.1700
Data Index: 588916 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1859. Min Range: -4.1859
Max Act: 4.1546. Min Act: -0.1700
Data Index: 886884 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1859. Min Range: -4.1859
Max Act: 4.0608. Min Act: -0.1700
Data Index: 1345770 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1859. Min Range: -4.1859
Max Act: 4.0296. Min Act: -0.1700
Data Index: 872825 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1859. Min Range: -4.1859
Max Act: 4.0296. Min Act: -0.1700
Data Index: 659412 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1603469 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.9045. Min Act: -0.1700
Data Index: 180308 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.9045. Min Act: -0.1700
Data Index: 1549246 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8419. Min Act: -0.1700
Data Index: 247530 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.7168. Min Act: -0.1700
Data Index: 845642 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1214602 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8732. Min Act: -0.1700
Data Index: 1563132 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.7168. Min Act: -0.1700
Data Index: 604709 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1443046 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.7794. Min Act: -0.1700
Data Index: 1588732 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8107. Min Act: -0.1700
Data Index: 1410347 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8419. Min Act: -0.1700
Data Index: 94831 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.7794. Min Act: -0.1700
Data Index: 1324738 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.8419. Min Act: -0.1700
Data Index: 130277 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1859. Min Range: -4.1859
Max Act: 3.7168. Min Act: -0.1700
Data Index: 1509597 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19