Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 16 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.9458. Min Act: -0.1700
Data Index: 1177996 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.8208. Min Act: -0.1700
Data Index: 151052 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.8208. Min Act: -0.1700
Data Index: 1964 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7896. Min Act: -0.1700
Data Index: 389415 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7896. Min Act: -0.1700
Data Index: 880850 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.8521. Min Act: -0.1700
Data Index: 956627 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7271. Min Act: -0.1700
Data Index: 1067987 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7583. Min Act: -0.1700
Data Index: 842611 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7896. Min Act: -0.1700
Data Index: 462490 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7583. Min Act: -0.1700
Data Index: 135782 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7896. Min Act: -0.1700
Data Index: 412808 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7271. Min Act: -0.1700
Data Index: 1000303 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.7271. Min Act: -0.1700
Data Index: 1348708 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6958. Min Act: -0.1700
Data Index: 1278757 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6646. Min Act: -0.1700
Data Index: 638823 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6646. Min Act: -0.1700
Data Index: 1250373 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6958. Min Act: -0.1700
Data Index: 1241300 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6958. Min Act: -0.1700
Data Index: 744109 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6021. Min Act: -0.1700
Data Index: 399719 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9458. Min Range: -4.9458
Max Act: 4.6333. Min Act: -0.1700
Data Index: 649628 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19