Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 19 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.1691. Min Act: -0.1700
Data Index: 283911 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0904. Min Act: -0.1700
Data Index: 756513 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0746. Min Act: -0.1700
Data Index: 704762 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0588. Min Act: -0.1700
Data Index: 192705 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0272. Min Act: -0.1700
Data Index: 83731 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0430. Min Act: -0.1700
Data Index: 508510 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0272. Min Act: -0.1700
Data Index: 565855 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0588. Min Act: -0.1700
Data Index: 427546 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0588. Min Act: -0.1700
Data Index: 580443 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0114. Min Act: -0.1700
Data Index: 823609 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1691. Min Range: -3.1691
Max Act: 3.0114. Min Act: -0.1700
Data Index: 1263771 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9956. Min Act: -0.1700
Data Index: 134977 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9640. Min Act: -0.1700
Data Index: 193798 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9798. Min Act: -0.1700
Data Index: 1022713 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9640. Min Act: -0.1700
Data Index: 134690 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9481. Min Act: -0.1700
Data Index: 169813 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9798. Min Act: -0.1700
Data Index: 360276 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9481. Min Act: -0.1700
Data Index: 917021 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9481. Min Act: -0.1700
Data Index: 1186281 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1691. Min Range: -3.1691
Max Act: 2.9323. Min Act: -0.1700
Data Index: 504721 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19