Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1540 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8880. Min Act: -0.1700
Data Index: 814481 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8721. Min Act: -0.1700
Data Index: 179395 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8244. Min Act: -0.1700
Data Index: 1137200 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8085. Min Act: -0.1700
Data Index: 923494 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8085. Min Act: -0.1700
Data Index: 334282 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.8085. Min Act: -0.1700
Data Index: 488199 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7926. Min Act: -0.1700
Data Index: 112141 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7926. Min Act: -0.1700
Data Index: 558778 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7926. Min Act: -0.1700
Data Index: 37633 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7766. Min Act: -0.1700
Data Index: 285277 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7766. Min Act: -0.1700
Data Index: 591340 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7607. Min Act: -0.1700
Data Index: 367851 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7447. Min Act: -0.1700
Data Index: 1160083 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7288. Min Act: -0.1700
Data Index: 317566 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7288. Min Act: -0.1699
Data Index: 1076365 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7128. Min Act: -0.1700
Data Index: 631573 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.7128. Min Act: -0.1700
Data Index: 351176 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.6968. Min Act: -0.1700
Data Index: 450204 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.6968. Min Act: -0.1700
Data Index: 112340 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8880. Min Range: -2.8880
Max Act: 2.6968. Min Act: -0.1700
Data Index: 41823 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19