Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2001 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.6037. Min Act: -0.1700
Data Index: 230752 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5097. Min Act: -0.1700
Data Index: 297178 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5410. Min Act: -0.1700
Data Index: 1256841 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5097. Min Act: -0.1700
Data Index: 1100128 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5567. Min Act: -0.1700
Data Index: 506442 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5410. Min Act: -0.1700
Data Index: 1024798 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4940. Min Act: -0.1700
Data Index: 79149 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.5097. Min Act: -0.1700
Data Index: 380022 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4940. Min Act: -0.1700
Data Index: 1125625 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4783. Min Act: -0.1700
Data Index: 879304 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4940. Min Act: -0.1700
Data Index: 1153895 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4783. Min Act: -0.1700
Data Index: 227087 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4783. Min Act: -0.1700
Data Index: 1003349 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4627. Min Act: -0.1700
Data Index: 1307848 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4783. Min Act: -0.1700
Data Index: 166945 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4627. Min Act: -0.1700
Data Index: 925021 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4783. Min Act: -0.1700
Data Index: 182950 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4627. Min Act: -0.1700
Data Index: 441026 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4940. Min Act: -0.1700
Data Index: 801052 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6037. Min Range: -3.6037
Max Act: 3.4313. Min Act: -0.1700
Data Index: 118483 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19