Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 79 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.3545. Min Act: -0.1700
Data Index: 1292746 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.2920. Min Act: -0.1700
Data Index: 493691 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.1983. Min Act: -0.1700
Data Index: 1157361 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.2608. Min Act: -0.1700
Data Index: 812779 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.2295. Min Act: -0.1700
Data Index: 1033029 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.1358. Min Act: -0.1700
Data Index: 104987 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0420. Min Act: -0.1700
Data Index: 1140490 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.1045. Min Act: -0.1700
Data Index: 1203413 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.1045. Min Act: -0.1700
Data Index: 495078 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1117956 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0733. Min Act: -0.1700
Data Index: 914154 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0733. Min Act: -0.1700
Data Index: 702111 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1108488 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0108. Min Act: -0.1700
Data Index: 211783 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0108. Min Act: -0.1700
Data Index: 486489 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0108. Min Act: -0.1700
Data Index: 756842 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1208762 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3545. Min Range: -5.3545
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1233047 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3545. Min Range: -5.3545
Max Act: 4.9795. Min Act: -0.1700
Data Index: 1024387 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3545. Min Range: -5.3545
Max Act: 4.9795. Min Act: -0.1700
Data Index: 872772 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19