Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1963 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.7131. Min Act: -0.1700
Data Index: 1098598 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.6506. Min Act: -0.1700
Data Index: 108344 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.6506. Min Act: -0.1700
Data Index: 721979 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.5569. Min Act: -0.1700
Data Index: 280456 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.5256. Min Act: -0.1700
Data Index: 940209 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.5256. Min Act: -0.1700
Data Index: 1283143 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.4944. Min Act: -0.1700
Data Index: 770033 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.4631. Min Act: -0.1700
Data Index: 1179380 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.4318. Min Act: -0.1700
Data Index: 57751 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.4318. Min Act: -0.1700
Data Index: 608707 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.4006. Min Act: -0.1700
Data Index: 1059207 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3693. Min Act: -0.1700
Data Index: 108869 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3693. Min Act: -0.1700
Data Index: 118848 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3693. Min Act: -0.1700
Data Index: 1270275 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3693. Min Act: -0.1700
Data Index: 1194148 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3693. Min Act: -0.1700
Data Index: 1085150 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3381. Min Act: -0.1700
Data Index: 1182033 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3068. Min Act: -0.1700
Data Index: 919202 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3068. Min Act: -0.1700
Data Index: 114829 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7131. Min Range: -4.7131
Max Act: 4.3068. Min Act: -0.1700
Data Index: 866649 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19