Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1863 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.6732. Min Act: -0.1700
Data Index: 948364 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.6571. Min Act: -0.1700
Data Index: 98570 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5768. Min Act: -0.1700
Data Index: 141458 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5768. Min Act: -0.1700
Data Index: 1272181 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5445. Min Act: -0.1700
Data Index: 940634 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5606. Min Act: -0.1700
Data Index: 319280 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5768. Min Act: -0.1700
Data Index: 1344074 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5445. Min Act: -0.1700
Data Index: 1065747 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5283. Min Act: -0.1700
Data Index: 431801 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5122. Min Act: -0.1700
Data Index: 691281 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5283. Min Act: -0.1700
Data Index: 1083345 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5283. Min Act: -0.1700
Data Index: 854451 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5283. Min Act: -0.1700
Data Index: 84518 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5122. Min Act: -0.1700
Data Index: 328876 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5122. Min Act: -0.1700
Data Index: 1336748 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.5122. Min Act: -0.1700
Data Index: 382275 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.4960. Min Act: -0.1700
Data Index: 808579 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.4798. Min Act: -0.1700
Data Index: 1060830 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.4798. Min Act: -0.1700
Data Index: 865971 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6732. Min Range: -2.6732
Max Act: 2.4798. Min Act: -0.1700
Data Index: 322544 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19