Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 273 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.5444. Min Act: -0.1700
Data Index: 400630 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.3256. Min Act: -0.1700
Data Index: 876609 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.2944. Min Act: -0.1700
Data Index: 1198495 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.2006. Min Act: -0.1700
Data Index: 508803 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.2006. Min Act: -0.1700
Data Index: 1773 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.2318. Min Act: -0.1700
Data Index: 1337459 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1693. Min Act: -0.1700
Data Index: 276630 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1693. Min Act: -0.1700
Data Index: 1005396 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1693. Min Act: -0.1699
Data Index: 1010811 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1381. Min Act: -0.1700
Data Index: 36822 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1381. Min Act: -0.1700
Data Index: 470341 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1381. Min Act: -0.1700
Data Index: 666518 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1068. Min Act: -0.1700
Data Index: 412102 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.0756. Min Act: -0.1700
Data Index: 1084907 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1068. Min Act: -0.1699
Data Index: 478773 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1381. Min Act: -0.1700
Data Index: 573595 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.0130. Min Act: -0.1700
Data Index: 387207 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.0756. Min Act: -0.1700
Data Index: 947298 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.1068. Min Act: -0.1700
Data Index: 384786 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5444. Min Range: -4.5444
Max Act: 4.0756. Min Act: -0.1700
Data Index: 428076 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19