Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1968 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.8033. Min Act: -0.1700
Data Index: 17682 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.7235. Min Act: -0.1700
Data Index: 1138800 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.7395. Min Act: -0.1700
Data Index: 1071783 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.7075. Min Act: -0.1700
Data Index: 1189746 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.7075. Min Act: -0.1700
Data Index: 938398 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6915. Min Act: -0.1700
Data Index: 1000101 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6915. Min Act: -0.1700
Data Index: 342915 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6915. Min Act: -0.1700
Data Index: 891802 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6755. Min Act: -0.1700
Data Index: 634399 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6915. Min Act: -0.1700
Data Index: 1261028 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6755. Min Act: -0.1700
Data Index: 158585 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6595. Min Act: -0.1700
Data Index: 1011263 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6274. Min Act: -0.1700
Data Index: 1092985 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6755. Min Act: -0.1700
Data Index: 36797 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6434. Min Act: -0.1700
Data Index: 1156868 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6434. Min Act: -0.1700
Data Index: 765117 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6434. Min Act: -0.1700
Data Index: 119809 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6274. Min Act: -0.1700
Data Index: 1020900 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6434. Min Act: -0.1700
Data Index: 711813 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8033. Min Range: -2.8033
Max Act: 2.6434. Min Act: -0.1700
Data Index: 513027 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19