Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1416 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.7651. Min Act: -0.1700
Data Index: 1082910 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.7338. Min Act: -0.1700
Data Index: 806476 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.6713. Min Act: -0.1700
Data Index: 590105 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.6401. Min Act: -0.1700
Data Index: 246433 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.5776. Min Act: -0.1700
Data Index: 446198 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.5463. Min Act: -0.1700
Data Index: 650794 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.5463. Min Act: -0.1700
Data Index: 9567 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.6088. Min Act: -0.1700
Data Index: 878684 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4838. Min Act: -0.1700
Data Index: 687925 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4213. Min Act: -0.1700
Data Index: 314569 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4526. Min Act: -0.1700
Data Index: 597663 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4213. Min Act: -0.1700
Data Index: 874968 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.5151. Min Act: -0.1700
Data Index: 375091 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4838. Min Act: -0.1700
Data Index: 925364 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4526. Min Act: -0.1700
Data Index: 33436 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4838. Min Act: -0.1700
Data Index: 796066 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4213. Min Act: -0.1700
Data Index: 796170 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.2963. Min Act: -0.1700
Data Index: 949176 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4526. Min Act: -0.1700
Data Index: 364224 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7651. Min Range: -4.7651
Max Act: 4.4838. Min Act: -0.1700
Data Index: 1122041 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19