Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1889 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.8521. Min Act: -0.1700
Data Index: 660022 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.8362. Min Act: -0.1700
Data Index: 876903 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.8362. Min Act: -0.1700
Data Index: 196509 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7725. Min Act: -0.1700
Data Index: 372470 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7725. Min Act: -0.1700
Data Index: 50039 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7405. Min Act: -0.1700
Data Index: 1177966 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7565. Min Act: -0.1700
Data Index: 1116074 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 1148896 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 424056 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7565. Min Act: -0.1700
Data Index: 958042 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 1212083 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 815993 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7405. Min Act: -0.1700
Data Index: 1175749 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 69698 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7405. Min Act: -0.1700
Data Index: 996586 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7405. Min Act: -0.1700
Data Index: 940424 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.6926. Min Act: -0.1700
Data Index: 598523 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7246. Min Act: -0.1700
Data Index: 868401 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.7086. Min Act: -0.1700
Data Index: 505103 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8521. Min Range: -2.8521
Max Act: 2.6926. Min Act: -0.1700
Data Index: 527649 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19