Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1880. Min Range: -4.1880
Max Act: 4.1880. Min Act: -0.1700
Data Index: 220176 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.9692. Min Act: -0.1700
Data Index: 631198 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.9067. Min Act: -0.1700
Data Index: 205919 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.8128. Min Act: -0.1700
Data Index: 565052 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.8441. Min Act: -0.1700
Data Index: 850502 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7816. Min Act: -0.1700
Data Index: 1343098 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7503. Min Act: -0.1700
Data Index: 637084 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7816. Min Act: -0.1700
Data Index: 406328 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.8128. Min Act: -0.1700
Data Index: 490537 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7816. Min Act: -0.1700
Data Index: 341206 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 833546 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7503. Min Act: -0.1700
Data Index: 851632 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 568234 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7190. Min Act: -0.1700
Data Index: 741469 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 461745 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 958387 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 74400 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 1144828 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.7190. Min Act: -0.1700
Data Index: 281083 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1880. Min Range: -4.1880
Max Act: 3.6877. Min Act: -0.1700
Data Index: 1273437 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19