Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1776 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1504. Min Act: -0.1700
Data Index: 445109 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0242. Min Act: -0.1700
Data Index: 362564 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9610. Min Act: -0.1700
Data Index: 1227834 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9293. Min Act: -0.1700
Data Index: 107607 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9135. Min Act: -0.1700
Data Index: 366330 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9451. Min Act: -0.1700
Data Index: 677426 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9610. Min Act: -0.1700
Data Index: 959451 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9135. Min Act: -0.1700
Data Index: 207037 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.9135. Min Act: -0.1700
Data Index: 981904 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8976. Min Act: -0.1700
Data Index: 819875 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8817. Min Act: -0.1700
Data Index: 134487 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8817. Min Act: -0.1700
Data Index: 206317 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8976. Min Act: -0.1700
Data Index: 753800 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8658. Min Act: -0.1700
Data Index: 960013 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8500. Min Act: -0.1700
Data Index: 520276 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8658. Min Act: -0.1700
Data Index: 1049426 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8658. Min Act: -0.1700
Data Index: 762035 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8658. Min Act: -0.1700
Data Index: 412224 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8500. Min Act: -0.1700
Data Index: 287046 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1504. Min Range: -3.1504
Max Act: 2.8182. Min Act: -0.1700
Data Index: 230887 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19