Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1583 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.2157. Min Act: -0.1700
Data Index: 850940 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.2470. Min Act: -0.1700
Data Index: 1307431 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.2157. Min Act: -0.1700
Data Index: 199444 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.2470. Min Act: -0.1700
Data Index: 1058949 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.2157. Min Act: -0.1700
Data Index: 195485 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.1532. Min Act: -0.1700
Data Index: 1053424 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.1845. Min Act: -0.1700
Data Index: 1280504 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.1219. Min Act: -0.1700
Data Index: 654684 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.1532. Min Act: -0.1700
Data Index: 991625 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0907. Min Act: -0.1700
Data Index: 23459 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0594. Min Act: -0.1700
Data Index: 1103931 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0907. Min Act: -0.1700
Data Index: 1081707 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0594. Min Act: -0.1700
Data Index: 1050537 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2470. Min Range: -4.2470
Max Act: 3.9969. Min Act: -0.1700
Data Index: 7900 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0281. Min Act: -0.1700
Data Index: 58026 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2470. Min Range: -4.2470
Max Act: 3.9969. Min Act: -0.1700
Data Index: 1210590 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0281. Min Act: -0.1700
Data Index: 517563 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0281. Min Act: -0.1700
Data Index: 898619 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2470. Min Range: -4.2470
Max Act: 3.9969. Min Act: -0.1700
Data Index: 843584 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2470. Min Range: -4.2470
Max Act: 4.0594. Min Act: -0.1700
Data Index: 888475 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19