Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2042 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0618. Min Range: -3.0618
Max Act: 3.0618. Min Act: -0.1700
Data Index: 447574 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9353. Min Act: -0.1700
Data Index: 1058006 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9511. Min Act: -0.1700
Data Index: 668406 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9353. Min Act: -0.1700
Data Index: 658445 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9195. Min Act: -0.1700
Data Index: 1145013 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9036. Min Act: -0.1700
Data Index: 1134895 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8877. Min Act: -0.1700
Data Index: 737944 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.9036. Min Act: -0.1700
Data Index: 206156 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8560. Min Act: -0.1700
Data Index: 331005 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8242. Min Act: -0.1700
Data Index: 24946 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8242. Min Act: -0.1700
Data Index: 979671 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8242. Min Act: -0.1700
Data Index: 1306203 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8242. Min Act: -0.1700
Data Index: 39864 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8083. Min Act: -0.1700
Data Index: 1120805 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8083. Min Act: -0.1700
Data Index: 1343715 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.8083. Min Act: -0.1700
Data Index: 215711 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.7923. Min Act: -0.1700
Data Index: 1323844 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.7923. Min Act: -0.1700
Data Index: 17751 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.7605. Min Act: -0.1700
Data Index: 1083134 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0618. Min Range: -3.0618
Max Act: 2.7764. Min Act: -0.1700
Data Index: 1071007 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19