Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 866 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.3482. Min Act: -0.1700
Data Index: 410379 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.2232. Min Act: -0.1700
Data Index: 224799 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.2232. Min Act: -0.1700
Data Index: 1270785 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1919. Min Act: -0.1700
Data Index: 193762 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1919. Min Act: -0.1700
Data Index: 903784 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1919. Min Act: -0.1700
Data Index: 843332 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1606. Min Act: -0.1700
Data Index: 1132666 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1606. Min Act: -0.1700
Data Index: 783088 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 784039 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 503678 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 291899 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 604104 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1606. Min Act: -0.1700
Data Index: 691240 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 232116 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.0981. Min Act: -0.1700
Data Index: 316393 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.0981. Min Act: -0.1700
Data Index: 276102 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.0669. Min Act: -0.1700
Data Index: 129378 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.0669. Min Act: -0.1700
Data Index: 1016461 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.0981. Min Act: -0.1700
Data Index: 1005709 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3482. Min Range: -4.3482
Max Act: 4.1294. Min Act: -0.1700
Data Index: 1293250 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19