Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2029 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3691. Min Act: -0.1700
Data Index: 619651 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3066. Min Act: -0.1700
Data Index: 1271584 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3691. Min Act: -0.1700
Data Index: 115917 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3379. Min Act: -0.1700
Data Index: 733715 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2441. Min Act: -0.1700
Data Index: 929567 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3223. Min Act: -0.1700
Data Index: 52733 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2754. Min Act: -0.1700
Data Index: 155612 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.3379. Min Act: -0.1700
Data Index: 682544 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2285. Min Act: -0.1700
Data Index: 354675 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2285. Min Act: -0.1700
Data Index: 34536 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2598. Min Act: -0.1700
Data Index: 465596 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1972. Min Act: -0.1700
Data Index: 956753 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1972. Min Act: -0.1700
Data Index: 81715 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1972. Min Act: -0.1700
Data Index: 295742 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1347. Min Act: -0.1700
Data Index: 758615 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.2598. Min Act: -0.1700
Data Index: 315487 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1504. Min Act: -0.1700
Data Index: 485473 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.0878. Min Act: -0.1700
Data Index: 1208566 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1504. Min Act: -0.1700
Data Index: 91276 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3691. Min Range: -4.3691
Max Act: 4.1504. Min Act: -0.1700
Data Index: 850421 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19