Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 280 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0122. Min Range: -3.0122
Max Act: 3.0122. Min Act: -0.1700
Data Index: 847525 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9172. Min Act: -0.1700
Data Index: 948945 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9172. Min Act: -0.1700
Data Index: 959048 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8855. Min Act: -0.1700
Data Index: 790791 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8696. Min Act: -0.1700
Data Index: 897767 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8696. Min Act: -0.1700
Data Index: 1098065 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8696. Min Act: -0.1700
Data Index: 1062153 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8696. Min Act: -0.1700
Data Index: 803541 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8537. Min Act: -0.1700
Data Index: 871790 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8219. Min Act: -0.1700
Data Index: 963034 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8219. Min Act: -0.1700
Data Index: 445989 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8219. Min Act: -0.1700
Data Index: 1035320 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8060. Min Act: -0.1700
Data Index: 1310602 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8060. Min Act: -0.1700
Data Index: 589925 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.7901. Min Act: -0.1700
Data Index: 98444 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.8060. Min Act: -0.1700
Data Index: 515284 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.7901. Min Act: -0.1700
Data Index: 669001 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.7901. Min Act: -0.1700
Data Index: 1062753 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.7901. Min Act: -0.1700
Data Index: 783824 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.7901. Min Act: -0.1700
Data Index: 28311 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19