Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1961 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9776. Min Act: -0.1700
Data Index: 1245346 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9618. Min Act: -0.1700
Data Index: 404941 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9460. Min Act: -0.1700
Data Index: 1646457 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9301. Min Act: -0.1700
Data Index: 598563 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9143. Min Act: -0.1700
Data Index: 709586 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.9460. Min Act: -0.1700
Data Index: 1113187 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8984. Min Act: -0.1700
Data Index: 165255 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8984. Min Act: -0.1700
Data Index: 826575 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8826. Min Act: -0.1700
Data Index: 434710 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8984. Min Act: -0.1700
Data Index: 755484 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8508. Min Act: -0.1700
Data Index: 736917 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8508. Min Act: -0.1700
Data Index: 670655 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8508. Min Act: -0.1700
Data Index: 1132349 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8667. Min Act: -0.1700
Data Index: 1330756 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8349. Min Act: -0.1700
Data Index: 1051633 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8190. Min Act: -0.1700
Data Index: 614715 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8190. Min Act: -0.1700
Data Index: 153659 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8190. Min Act: -0.1700
Data Index: 876762 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8190. Min Act: -0.1700
Data Index: 6616 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9776. Min Range: -2.9776
Max Act: 2.8190. Min Act: -0.1700
Data Index: 688860 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19