Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 411 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2870. Min Act: -0.1700
Data Index: 736051 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2870. Min Act: -0.1700
Data Index: 512738 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2870. Min Act: -0.1700
Data Index: 319199 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2540. Min Act: -0.1700
Data Index: 1599903 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2705. Min Act: -0.1700
Data Index: 162498 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2705. Min Act: -0.1700
Data Index: 1099273 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2375. Min Act: -0.1700
Data Index: 484733 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2044. Min Act: -0.1700
Data Index: 305793 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2209. Min Act: -0.1700
Data Index: 1207641 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.2044. Min Act: -0.1700
Data Index: 467333 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1878. Min Act: -0.1700
Data Index: 1587848 (Python Code)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1712. Min Act: -0.1700
Data Index: 319715 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1878. Min Act: -0.1700
Data Index: 147269 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1545. Min Act: -0.1700
Data Index: 1455281 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1712. Min Act: -0.1700
Data Index: 831843 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1712. Min Act: -0.1700
Data Index: 672382 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1712. Min Act: -0.1700
Data Index: 462984 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1712. Min Act: -0.1700
Data Index: 271430 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1545. Min Act: -0.1700
Data Index: 1205074 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2870. Min Range: -2.2870
Max Act: 2.1545. Min Act: -0.1700
Data Index: 1628105 (Python Code)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19