Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1851 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.7896. Min Act: -0.1700
Data Index: 417110 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.7896. Min Act: -0.1700
Data Index: 129133 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.6959. Min Act: -0.1700
Data Index: 534801 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.6334. Min Act: -0.1700
Data Index: 881691 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.6646. Min Act: -0.1700
Data Index: 330407 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.6334. Min Act: -0.1700
Data Index: 969302 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 1223034 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 14981 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.6021. Min Act: -0.1700
Data Index: 567486 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 138346 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 132202 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 541220 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5709. Min Act: -0.1700
Data Index: 1022257 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 1206557 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 153986 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 308541 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 358402 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5084. Min Act: -0.1700
Data Index: 560793 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 1171318 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7896. Min Range: -4.7896
Max Act: 4.5396. Min Act: -0.1700
Data Index: 69070 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19