Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 49 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2409. Min Range: -6.2409
Max Act: 6.2409. Min Act: -0.1700
Data Index: 442257 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2409. Min Range: -6.2409
Max Act: 6.0534. Min Act: -0.1700
Data Index: 63716 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2409. Min Range: -6.2409
Max Act: 6.0534. Min Act: -0.1700
Data Index: 1201075 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8346. Min Act: -0.1700
Data Index: 1412851 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2409. Min Range: -6.2409
Max Act: 6.0846. Min Act: -0.1700
Data Index: 1195570 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8346. Min Act: -0.1700
Data Index: 1097113 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8659. Min Act: -0.1700
Data Index: 599243 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8971. Min Act: -0.1700
Data Index: 4287 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8346. Min Act: -0.1700
Data Index: 1482054 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7096. Min Act: -0.1700
Data Index: 906654 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8346. Min Act: -0.1700
Data Index: 434040 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7096. Min Act: -0.1700
Data Index: 170184 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7721. Min Act: -0.1700
Data Index: 488339 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7409. Min Act: -0.1700
Data Index: 1204319 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7409. Min Act: -0.1700
Data Index: 1171129 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1081654 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.6784. Min Act: -0.1700
Data Index: 87057 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.8034. Min Act: -0.1700
Data Index: 403635 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7721. Min Act: -0.1700
Data Index: 33981 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2409. Min Range: -6.2409
Max Act: 5.7096. Min Act: -0.1700
Data Index: 312421 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19