Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1879 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.7259. Min Act: -0.1700
Data Index: 480359 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.7259. Min Act: -0.1700
Data Index: 914773 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.6779. Min Act: -0.1700
Data Index: 376862 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.6619. Min Act: -0.1700
Data Index: 314684 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5976. Min Act: -0.1700
Data Index: 336497 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.6137. Min Act: -0.1700
Data Index: 1022232 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.6137. Min Act: -0.1700
Data Index: 1310613 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.6137. Min Act: -0.1700
Data Index: 877524 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5976. Min Act: -0.1700
Data Index: 136498 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5976. Min Act: -0.1700
Data Index: 460247 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5976. Min Act: -0.1700
Data Index: 668153 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5815. Min Act: -0.1700
Data Index: 632625 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5654. Min Act: -0.1700
Data Index: 165035 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5815. Min Act: -0.1700
Data Index: 102717 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5815. Min Act: -0.1700
Data Index: 1241460 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5654. Min Act: -0.1700
Data Index: 1529569 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5654. Min Act: -0.1700
Data Index: 394597 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5654. Min Act: -0.1700
Data Index: 166058 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5492. Min Act: -0.1700
Data Index: 370087 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7259. Min Range: -2.7259
Max Act: 2.5492. Min Act: -0.1700
Data Index: 201464 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19