Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2041 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9951. Min Act: -0.1700
Data Index: 17299 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9793. Min Act: -0.1700
Data Index: 28079 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9793. Min Act: -0.1700
Data Index: 892763 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 699164 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 1301882 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 1052926 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 779820 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 728861 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 1297395 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9635. Min Act: -0.1700
Data Index: 1234208 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 305028 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9477. Min Act: -0.1700
Data Index: 647486 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9477. Min Act: -0.1700
Data Index: 524258 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9477. Min Act: -0.1700
Data Index: 718621 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9477. Min Act: -0.1700
Data Index: 549848 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 627078 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 305789 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 302495 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 1159629 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9951. Min Range: -2.9951
Max Act: 2.9318. Min Act: -0.1700
Data Index: 655581 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19