Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 125 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.7888. Min Act: -0.1700
Data Index: 423366 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.7888. Min Act: -0.1700
Data Index: 337738 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.7410. Min Act: -0.1700
Data Index: 1122985 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.7410. Min Act: -0.1700
Data Index: 841522 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.7090. Min Act: -0.1700
Data Index: 1212927 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6770. Min Act: -0.1700
Data Index: 569985 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6609. Min Act: -0.1700
Data Index: 671177 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6770. Min Act: -0.1700
Data Index: 674465 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6609. Min Act: -0.1700
Data Index: 82791 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6449. Min Act: -0.1700
Data Index: 869112 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6770. Min Act: -0.1700
Data Index: 947117 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6449. Min Act: -0.1700
Data Index: 342132 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6609. Min Act: -0.1699
Data Index: 546605 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6449. Min Act: -0.1700
Data Index: 671455 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6449. Min Act: -0.1700
Data Index: 599017 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6288. Min Act: -0.1700
Data Index: 703157 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6288. Min Act: -0.1700
Data Index: 455516 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6288. Min Act: -0.1700
Data Index: 150864 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6288. Min Act: -0.1700
Data Index: 840408 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7888. Min Range: -2.7888
Max Act: 2.6609. Min Act: -0.1700
Data Index: 1077817 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19