Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1704 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.1681. Min Act: -0.1700
Data Index: 1264048 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0735. Min Act: -0.1700
Data Index: 671754 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0419. Min Act: -0.1700
Data Index: 393975 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0103. Min Act: -0.1700
Data Index: 298319 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0103. Min Act: -0.1700
Data Index: 707887 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0103. Min Act: -0.1700
Data Index: 327711 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.9787. Min Act: -0.1700
Data Index: 1238282 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.9629. Min Act: -0.1700
Data Index: 273109 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1681. Min Range: -3.1681
Max Act: 3.0103. Min Act: -0.1700
Data Index: 1048789 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.9787. Min Act: -0.1700
Data Index: 256013 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.9312. Min Act: -0.1700
Data Index: 728773 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.9312. Min Act: -0.1700
Data Index: 161383 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8995. Min Act: -0.1700
Data Index: 1108376 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8836. Min Act: -0.1700
Data Index: 731540 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8519. Min Act: -0.1700
Data Index: 271515 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8678. Min Act: -0.1700
Data Index: 1019777 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8995. Min Act: -0.1700
Data Index: 818384 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8519. Min Act: -0.1700
Data Index: 9556 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8519. Min Act: -0.1700
Data Index: 1001217 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1681. Min Range: -3.1681
Max Act: 2.8360. Min Act: -0.1700
Data Index: 817347 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19