Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 132 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.6560. Min Act: -0.1699
Data Index: 7184 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.6247. Min Act: -0.1700
Data Index: 926185 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4684. Min Act: -0.1699
Data Index: 641410 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4372. Min Act: -0.1700
Data Index: 1041683 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4684. Min Act: -0.1700
Data Index: 33370 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4997. Min Act: -0.1700
Data Index: 1141693 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4059. Min Act: -0.1700
Data Index: 1008531 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 67578 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4059. Min Act: -0.1700
Data Index: 394737 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4059. Min Act: -0.1700
Data Index: 725080 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 1018769 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4372. Min Act: -0.1700
Data Index: 1109342 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3434. Min Act: -0.1700
Data Index: 717233 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4059. Min Act: -0.1700
Data Index: 1321346 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.4059. Min Act: -0.1700
Data Index: 320334 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 349723 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 1159476 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 335321 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3747. Min Act: -0.1700
Data Index: 1029642 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6560. Min Range: -4.6560
Max Act: 4.3434. Min Act: -0.1699
Data Index: 869325 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19