Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1916 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.7594. Min Act: -0.1700
Data Index: 311094 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.7434. Min Act: -0.1700
Data Index: 646539 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6474. Min Act: -0.1700
Data Index: 1296139 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6634. Min Act: -0.1700
Data Index: 751689 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6634. Min Act: -0.1700
Data Index: 660572 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6474. Min Act: -0.1700
Data Index: 1026242 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6474. Min Act: -0.1700
Data Index: 1060994 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6474. Min Act: -0.1700
Data Index: 65250 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6474. Min Act: -0.1700
Data Index: 550458 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6152. Min Act: -0.1700
Data Index: 1144353 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6313. Min Act: -0.1700
Data Index: 972293 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.5991. Min Act: -0.1700
Data Index: 842781 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6152. Min Act: -0.1700
Data Index: 339377 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6152. Min Act: -0.1700
Data Index: 887831 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6152. Min Act: -0.1700
Data Index: 491400 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.5991. Min Act: -0.1700
Data Index: 653791 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.5830. Min Act: -0.1700
Data Index: 96534 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.5830. Min Act: -0.1700
Data Index: 716548 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.6152. Min Act: -0.1700
Data Index: 722950 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7594. Min Range: -2.7594
Max Act: 2.5830. Min Act: -0.1700
Data Index: 493971 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19