Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 456 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.3128. Min Act: -0.1700
Data Index: 235996 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.2816. Min Act: -0.1700
Data Index: 651933 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 569117 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.2191. Min Act: -0.1700
Data Index: 1345768 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 307683 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1566. Min Act: -0.1700
Data Index: 727432 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1166046 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1878. Min Act: -0.1700
Data Index: 956660 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1289552 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 284810 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 236090 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.0941. Min Act: -0.1700
Data Index: 193368 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 69820 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.0941. Min Act: -0.1700
Data Index: 777728 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.0316. Min Act: -0.1700
Data Index: 989176 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.0316. Min Act: -0.1699
Data Index: 145123 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3128. Min Range: -6.3128
Max Act: 6.0003. Min Act: -0.1700
Data Index: 1001737 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3128. Min Range: -6.3128
Max Act: 5.9378. Min Act: -0.1700
Data Index: 1085523 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3128. Min Range: -6.3128
Max Act: 5.9691. Min Act: -0.1700
Data Index: 1281158 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3128. Min Range: -6.3128
Max Act: 5.9378. Min Act: -0.1700
Data Index: 574180 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19