Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.3847. Min Act: -0.1700
Data Index: 105071 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.3028. Min Act: -0.1700
Data Index: 359866 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.3028. Min Act: -0.1700
Data Index: 966996 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.3028. Min Act: -0.1700
Data Index: 961654 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.3028. Min Act: -0.1700
Data Index: 568550 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2863. Min Act: -0.1700
Data Index: 736909 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2863. Min Act: -0.1700
Data Index: 931389 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2863. Min Act: -0.1700
Data Index: 910845 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2699. Min Act: -0.1700
Data Index: 1195115 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2534. Min Act: -0.1700
Data Index: 596884 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2534. Min Act: -0.1700
Data Index: 722714 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2534. Min Act: -0.1700
Data Index: 1112214 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2534. Min Act: -0.1700
Data Index: 985955 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2368. Min Act: -0.1700
Data Index: 1769 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2368. Min Act: -0.1700
Data Index: 535757 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2203. Min Act: -0.1700
Data Index: 1016287 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2368. Min Act: -0.1700
Data Index: 749249 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2368. Min Act: -0.1700
Data Index: 372276 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2203. Min Act: -0.1700
Data Index: 647261 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3847. Min Range: -2.3847
Max Act: 2.2203. Min Act: -0.1700
Data Index: 287754 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19