Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1952 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0927. Min Range: -4.0927
Max Act: 4.0927. Min Act: -0.1700
Data Index: 1326352 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0927. Min Range: -4.0927
Max Act: 4.0614. Min Act: -0.1700
Data Index: 857980 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0927. Min Range: -4.0927
Max Act: 4.0301. Min Act: -0.1700
Data Index: 397707 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9989. Min Act: -0.1700
Data Index: 576495 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0927. Min Range: -4.0927
Max Act: 4.0301. Min Act: -0.1700
Data Index: 888057 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9676. Min Act: -0.1700
Data Index: 855700 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9989. Min Act: -0.1700
Data Index: 1296392 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9676. Min Act: -0.1700
Data Index: 625597 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9676. Min Act: -0.1700
Data Index: 295749 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9363. Min Act: -0.1700
Data Index: 565086 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1347507 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1249220 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.8738. Min Act: -0.1700
Data Index: 1295549 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9676. Min Act: -0.1700
Data Index: 1083748 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1211700 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9363. Min Act: -0.1700
Data Index: 381690 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9051. Min Act: -0.1700
Data Index: 335978 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.9363. Min Act: -0.1700
Data Index: 1230426 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.8738. Min Act: -0.1700
Data Index: 401786 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0927. Min Range: -4.0927
Max Act: 3.8738. Min Act: -0.1700
Data Index: 1280150 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19