Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1048 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.4220. Min Act: -0.1700
Data Index: 160735 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.4220. Min Act: -0.1700
Data Index: 884288 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.3282. Min Act: -0.1700
Data Index: 1110918 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.3282. Min Act: -0.1700
Data Index: 82323 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.3282. Min Act: -0.1700
Data Index: 77647 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.3595. Min Act: -0.1700
Data Index: 746176 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2344. Min Act: -0.1700
Data Index: 639942 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2657. Min Act: -0.1700
Data Index: 1231256 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2657. Min Act: -0.1700
Data Index: 424331 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.3282. Min Act: -0.1700
Data Index: 700255 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2344. Min Act: -0.1700
Data Index: 1000802 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.1719. Min Act: -0.1700
Data Index: 1125052 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2344. Min Act: -0.1700
Data Index: 1207740 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2032. Min Act: -0.1700
Data Index: 228485 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2344. Min Act: -0.1700
Data Index: 857168 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2032. Min Act: -0.1700
Data Index: 260865 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2032. Min Act: -0.1700
Data Index: 1214251 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.1719. Min Act: -0.1700
Data Index: 994325 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2032. Min Act: -0.1700
Data Index: 886194 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4220. Min Range: -4.4220
Max Act: 4.2032. Min Act: -0.1700
Data Index: 712295 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19