Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 736 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.8646. Min Act: -0.1700
Data Index: 239824 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.8646. Min Act: -0.1700
Data Index: 680068 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.8010. Min Act: -0.1700
Data Index: 1021456 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.8169. Min Act: -0.1700
Data Index: 1178811 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7851. Min Act: -0.1700
Data Index: 1056592 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7851. Min Act: -0.1700
Data Index: 1146503 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7372. Min Act: -0.1700
Data Index: 505160 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7532. Min Act: -0.1700
Data Index: 1273095 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7532. Min Act: -0.1700
Data Index: 653940 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7532. Min Act: -0.1700
Data Index: 356885 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7372. Min Act: -0.1700
Data Index: 342265 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7052. Min Act: -0.1700
Data Index: 1071660 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7372. Min Act: -0.1700
Data Index: 1246305 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7372. Min Act: -0.1700
Data Index: 1273513 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7212. Min Act: -0.1700
Data Index: 702259 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7212. Min Act: -0.1700
Data Index: 1061350 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7052. Min Act: -0.1700
Data Index: 62577 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7372. Min Act: -0.1700
Data Index: 873046 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7212. Min Act: -0.1700
Data Index: 1026832 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8646. Min Range: -2.8646
Max Act: 2.7212. Min Act: -0.1700
Data Index: 44433 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19