Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 212 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.7491. Min Act: -0.1700
Data Index: 576500 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.7331. Min Act: -0.1700
Data Index: 1604843 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.7171. Min Act: -0.1700
Data Index: 626071 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.7171. Min Act: -0.1700
Data Index: 560670 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6691. Min Act: -0.1700
Data Index: 399719 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6691. Min Act: -0.1700
Data Index: 647327 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6370. Min Act: -0.1700
Data Index: 979260 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6370. Min Act: -0.1700
Data Index: 538446 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6370. Min Act: -0.1700
Data Index: 525445 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.6049. Min Act: -0.1700
Data Index: 806934 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 21014 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5888. Min Act: -0.1700
Data Index: 487718 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5888. Min Act: -0.1700
Data Index: 834588 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5888. Min Act: -0.1700
Data Index: 38515 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5888. Min Act: -0.1700
Data Index: 1295150 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 1248742 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 234970 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 208458 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 770692 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7491. Min Range: -2.7491
Max Act: 2.5727. Min Act: -0.1700
Data Index: 591108 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19