Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2045 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8207. Min Act: -0.1700
Data Index: 1176840 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8048. Min Act: -0.1700
Data Index: 267569 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8048. Min Act: -0.1700
Data Index: 921158 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8048. Min Act: -0.1700
Data Index: 776555 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8207. Min Act: -0.1700
Data Index: 1001193 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7888. Min Act: -0.1700
Data Index: 227619 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.8048. Min Act: -0.1700
Data Index: 1226662 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7729. Min Act: -0.1700
Data Index: 1006303 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7888. Min Act: -0.1700
Data Index: 349255 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7729. Min Act: -0.1700
Data Index: 793536 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7569. Min Act: -0.1700
Data Index: 709317 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7729. Min Act: -0.1700
Data Index: 115635 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7729. Min Act: -0.1700
Data Index: 129139 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7410. Min Act: -0.1700
Data Index: 346423 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7569. Min Act: -0.1700
Data Index: 740766 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7569. Min Act: -0.1700
Data Index: 232175 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7410. Min Act: -0.1700
Data Index: 173396 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7410. Min Act: -0.1700
Data Index: 5178 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7410. Min Act: -0.1700
Data Index: 678766 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8207. Min Range: -2.8207
Max Act: 2.7410. Min Act: -0.1700
Data Index: 111805 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19