Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 317 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0312. Min Range: -3.0312
Max Act: 3.0312. Min Act: -0.1700
Data Index: 1461148 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9996. Min Act: -0.1700
Data Index: 1068732 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9838. Min Act: -0.1700
Data Index: 1094376 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9838. Min Act: -0.1700
Data Index: 455842 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9838. Min Act: -0.1700
Data Index: 781896 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9680. Min Act: -0.1700
Data Index: 220177 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9521. Min Act: -0.1700
Data Index: 993114 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9363. Min Act: -0.1700
Data Index: 1139673 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9363. Min Act: -0.1700
Data Index: 527113 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9046. Min Act: -0.1700
Data Index: 54928 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9046. Min Act: -0.1700
Data Index: 1206687 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9046. Min Act: -0.1700
Data Index: 285830 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9046. Min Act: -0.1700
Data Index: 875323 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8887. Min Act: -0.1700
Data Index: 881071 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8729. Min Act: -0.1700
Data Index: 720107 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8887. Min Act: -0.1700
Data Index: 99094 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8729. Min Act: -0.1700
Data Index: 1292632 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.9046. Min Act: -0.1700
Data Index: 1563730 (Python Code)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8570. Min Act: -0.1700
Data Index: 1439008 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0312. Min Range: -3.0312
Max Act: 2.8729. Min Act: -0.1700
Data Index: 210746 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19