Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 21 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.2242. Min Act: -0.1700
Data Index: 516326 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.1305. Min Act: -0.1700
Data Index: 634872 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0992. Min Act: -0.1700
Data Index: 1099059 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.1305. Min Act: -0.1700
Data Index: 464131 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0992. Min Act: -0.1700
Data Index: 708227 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9741. Min Act: -0.1700
Data Index: 1122825 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0367. Min Act: -0.1700
Data Index: 48448 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0054. Min Act: -0.1700
Data Index: 1020445 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9741. Min Act: -0.1700
Data Index: 48141 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9741. Min Act: -0.1700
Data Index: 1335915 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0054. Min Act: -0.1700
Data Index: 1230481 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9741. Min Act: -0.1700
Data Index: 1322559 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9429. Min Act: -0.1700
Data Index: 1075840 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2242. Min Range: -4.2242
Max Act: 4.0054. Min Act: -0.1700
Data Index: 869320 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9116. Min Act: -0.1700
Data Index: 667381 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9429. Min Act: -0.1700
Data Index: 866982 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.9116. Min Act: -0.1700
Data Index: 1321537 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1297735 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.8803. Min Act: -0.1700
Data Index: 262143 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2242. Min Range: -4.2242
Max Act: 3.8491. Min Act: -0.1700
Data Index: 227402 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19