Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 99 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.8976. Min Act: -0.1700
Data Index: 1206627 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.7863. Min Act: -0.1700
Data Index: 291462 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.7544. Min Act: -0.1700
Data Index: 1165347 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.7384. Min Act: -0.1700
Data Index: 181332 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.7384. Min Act: -0.1700
Data Index: 966198 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.7065. Min Act: -0.1700
Data Index: 1292012 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6905. Min Act: -0.1700
Data Index: 1157764 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6905. Min Act: -0.1700
Data Index: 915299 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6744. Min Act: -0.1700
Data Index: 1102264 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6905. Min Act: -0.1700
Data Index: 689890 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 205634 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6744. Min Act: -0.1700
Data Index: 1289253 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6744. Min Act: -0.1700
Data Index: 738890 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 584504 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 590773 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6744. Min Act: -0.1700
Data Index: 1340440 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 862942 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 72328 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6584. Min Act: -0.1700
Data Index: 184225 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8976. Min Range: -2.8976
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1120 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19