Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1027 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0555. Min Range: -4.0555
Max Act: 4.0555. Min Act: -0.1700
Data Index: 552652 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0555. Min Range: -4.0555
Max Act: 4.0242. Min Act: -0.1700
Data Index: 627208 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.9304. Min Act: -0.1700
Data Index: 833325 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1700
Data Index: 688627 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1700
Data Index: 893749 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8992. Min Act: -0.1700
Data Index: 1105146 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1699
Data Index: 813215 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.7428. Min Act: -0.1700
Data Index: 1163909 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1700
Data Index: 557017 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1698
Data Index: 858736 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1699
Data Index: 594914 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8679. Min Act: -0.1698
Data Index: 821730 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1699
Data Index: 9234 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8679. Min Act: -0.1700
Data Index: 1261227 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.7741. Min Act: -0.1700
Data Index: 56032 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8053. Min Act: -0.1700
Data Index: 272099 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.7741. Min Act: -0.1700
Data Index: 933339 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.7741. Min Act: -0.1700
Data Index: 1157847 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.8366. Min Act: -0.1700
Data Index: 646727 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0555. Min Range: -4.0555
Max Act: 3.7428. Min Act: -0.1700
Data Index: 285384 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19